Neural Networks - Multilayer Perceptron inference on Project Procurement Management in VUCA environments

Neural Networks - Multilayer Perceptron inference on Project Procurement Management in VUCA environments | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article Neural Networks - Multilayer Perceptron inference on Project Procurement Management in VUCA environments Stephen Turkson, Patience Aboagyewaa This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6996931/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Engineering, procurement and construction projects provide intricate and essential infrastructure and construction projects. Projects initiate change, project procurement management (PPM) serves as a stabilizing force, enhancing success rates by fostering agility, collaboration, and strategic resource allocation. This study utilizes Multilayer Perceptron (MLP) Neural Networks to forecast VUCA Risks in project procurement management and improve project procurement decision-making with AI-driven insight. The study employs a survey research design method to evaluate the performance of the MLP ANN model and predict project procurement management in VUCA environment using Multilayer Perceptron (MLP) Neural Networks. Findings show that a systematic procurement framework improves sustainability/resilience (Mean=4.01, SD=1.41). Leadership/governance (Mean=4.01, SD=1.00) and AI/IoT/blockchain (Mean=4.01, SD=1.00) are critical for procurement success. Also, approximately 74.5% and 25.5% of the entire dataset is used for the training and testing process, respectively, to create the MLP ANN model. The number of units in the input layer was 7, the number of units in the hidden layer was 1, the hidden layer activation function was a hyperbolic tangent, the number of units in the output layer was 1, the output layer activation function was Identity, and the error function was Sum of squares. Development Economics Neural Networks - Multilayer Perceptron Project Procurement Management VUCA environments Figures Figure 1 1. Introduction Engineering, procurement and construction projects provide intricate and essential infrastructure and construction projects. However, these projects face multiple challenges and uncertainties (VUCA) (Kabirifar & Mojtahedi, 2019 ; Latha, 2020 ; Imoni et al., 2023 ; Bentahar & Belhadi, 2025 ). The VUCA era, characterized by volatility, uncertainty, complexity, and ambiguity, presents a challenging and unpredictable world where organizations and businesses face potential risks and challenges (Gunnarsdóttir, 2021 ; Fridgeirsson et al., 2021 ). VUCA characterizes the hard conditions and circumstances within which organizations function. Volatility pertains to the unpredictability and instability of change; uncertainty denotes the absence of understanding regarding future occurrences and their ramifications; and complexity involves numerous interconnected components that create an intricate network of information and processes (Makudza et al., 2023 ; Dong & Qiu, 2024 ). Ultimately, ambiguity signifies an absence of precedent for forecasting due to insufficient knowledge and comprehension of the causes, impacts, and interrelations of occurrences (Álvarez-Espada et al., 2024 ). Typically, in engineering, procurement and construction projects, the widely known risks/vuca include inaccurate cost estimation for the engineering phase, imprecise time estimation for the engineering phase, deficiency of management and skilled personnel, design flaws, supplier failures, unsuitable and inadequate technical drawings, diminished design time and expedited transition to the execution phase, delays in obtaining the project's initial permits, inadequate feasibility studies, inexperienced project managers, alterations due to political events, internal policy modifications within the organization, changes to the project's scope, scarcity of essential resources, and shifts in the employer's requirements (Moon, 2020 ; Mabilu, 2021 ; Karatu, 2023 ). According to Gomes & Romão ( 2016 ), projects promote organizational changes, influencing the environment and product development. However, they often fail to meet goals, with 36% of global projects considered unsuccessful. These failures cost hundreds of billions of dollars annually, not limited to specific regions or industries. Consequently, although projects initiate change, project procurement management (PPM) serves as a stabilizing force, enhancing success rates by fostering agility, collaboration, and strategic resource allocation (Govindan et al., ( 2024 ). Project management is intertwined with procurement, and it has also been subject to considerable transformation from very low cost to least evaluated cost procurement for social and environmental sustainability (Willis, 2010 ; Roumboutsos, 2010 ). Project procurement management form an important topic in current academic, business, and political debates of improving the efficiency and effectiveness of project delivery on time and within budget (El-Sayegh, 2008 ; de Araújo et al., 2017 ). Procurement has undergone significant transformation since its emergence as a discipline predominantly within the manufacturing sector in the mid-twentieth century (Tassabehji & Moorhouse, 2008 ; Rane et al., 2020 ; Rane & Narvel, 2021). In the 1980s and 1990s, procurement procedures evolved due to globalized market demands, requiring companies to acquire various supplies like raw materials, components, and consumables (Herold et al., 2023 ). Project procurement improves agility in the procurement project procurement management (PPM) process, including all organizational divisions, including sales, marketing, engineering design, and production (Nissen, 2009 ; Maddi et al., 2013 ; Amirtash et al., 2021 ). Moreover, understanding behavioural characteristics of procurement professionals on projects, influencing procurement professionals on procurement project management, conflict management, and cultural awareness deemed to be a success factor for procurement project management (Bradley, 2016 ; Mwagike & Changalima, 2022 ). Also, appropriate safeguards and coordination mechanisms to succeed on procurement works on any building or civil project(s) is also a success factor for procurement project management (Buzzetto et al., 2020; Khairullah et al., 2022 ). According to Kafile (2018), project managers ought to strategically approach the procurement process to maximize the efficiency of a project by considering factors like timeline, quality of project, and budget. The present research premise is that project procurement management’s adverse environment on project success and the moderating role of the chosen management method. It assumes that globalization and rapid technological changes in the VUCA era cause changes in project environments, leading to a mismatch between management methods and project results (Kafile & Fore, 2018; Hussain et al., 2021 ). This study utilizes Multilayer Perceptron (MLP) Neural Networks to forecast VUCA Risks in project procurement management and improve project procurement decision-making with AI-driven insights (Govindan et al., 2024 ). This study theoretically enhances the literature on AI-augmented project procurement management (PPM) within the settings of engineering, procurement, and construction projects (Karatu, 2023 ). Artificial Neural Networks (ANNs) are computer systems designed to autonomously acquire abilities such as generating and discovering new information through learning, akin to the functions of the human brain, without external assistance (Zidan & Hady, 2018 ). Artificial Neural Networks can model nonlinearity without requiring any assumptions or prior knowledge regarding input and output variables (Rivals & Personnaz, 2003 ). Moreover, the Multilayer Perceptron (MLP) is among the most often employed artificial neural network models for addressing nonlinear issues. This feed-forward backpropagation network contains a minimum of one layer between the input and output layers. The weight values across the layers are adjusted to minimize the computed error during the backpropagation phase, following the assessment of the network's output and error in the forward propagation phase (Popescu et al., 2009 ). This work aimed to predict project procurement management in VUCA environment using Multilayer Perceptron (MLP) Neural Networks. 2. Materials and Methods The study employs a survey research design method to evaluate the performance of the MLP ANN model and predict project procurement management in VUCA environment using Multilayer Perceptron (MLP) Neural Networks. The study’s population comprises ofprocurement managers and tutors, project managers and project management lecturers and students, engineering and construction professionals and experts in Ghana. Thus, the convenience sampling technique used was to sample respondents who can provide accurate responses to the questions (Paarry et al., 2018 ). The questionnaire was distributed to the respondents via google forms - electronic, and each respondent was instructed to fill out the questionnaire and return it in 3 days’ time or earlier. 220 questionnaires were administered electronically to the sampled respondents and 200 responses were obtained, and the analysis was conducted using the Multilayer Perceptron (MLP) Neural Networks. 3. Results 3.1 Demographics From the Table 1 below, the results show that respondents to the survey were mostly men. A majority (79.8%) of respondents were male and (16.3%) were female. Also, Table 2 below show that 67 respondents were procurement professionals (32.2%) and 133 (63.9%) were Project/ Construction Managers. Table 1 Gender Gender Frequency Percent Female 34 16.3 Male 166 79.8 Total 200 100.0 Table 2 Occupation Occupation Frequency Percent Procurement Professional 67 32.2 Project/ Construction Manager 133 63.9 Total 200 100.0 3.2 Descriptive Statistics The Table 3 below shows descriptive statistics (based on N = 200 responses per item). Respondents strongly agree that a systematic procurement framework improves sustainability/resilience (Mean = 4.01, SD = 1.41). Leadership/governance (Mean = 4.01, SD = 1.00) and AI/IoT/blockchain (Mean = 4.01, SD = 1.00) are critical for procurement success. An integrated PM-procurement framework is essential for VUCA challenges (Mean = 4.01, SD = 1.00). Also, sustainability/resilience (Mean = 3.84, SD = 0.90–1.34) and hybrid Agile-Waterfall approaches (Mean = 3.84, SD = 1.07) are deemed important. Current PM-SCM integration gaps (Mean = 3.51, SD = 1.26) and Agile practices (Mean = 3.51, SD = 1.39) show consensus but with higher variability. Lower Agreement were data analytics (Mean = 3.34, SD = 1.38) and dynamic risk management (Mean = 3.34, SD = 1.25) are seen as less impactful, suggesting room for improvement. The results imply that prioritizing leadership, technology (AI/IoT), and integrated frameworks are high-impact areas with broad agreement. Table 3 Descriptive sttistics Descriptive Statistics N Mean Std. Deviation A systematic project procurement management framework would significantly improve engineering, construction and procurement sustainability and resilience 200 4.01 1.412 A structured project procurement management framework reduces inefficiencies and coordination problems in complex engineering, construction and procurement projects 200 3.68 1.374 Project procurement assist scheduling and delivery of precise and prompt information, particularly about lead times, schedules, and their modifications 200 3.68 1.374 Data analytics enables real-time insights and predictive capabilities, supporting proactive management of project procurement management activities 200 3.34 1.376 Project procurement management involves developing sustainable sourcing practices, diversifying suppliers, and creating contingency plans for critical supply chain nodes 200 3.84 1.343 Emphasizing resilience and sustainability ensures project procurement can withstand disruptions and contribute to long-term organisational goals 200 3.84 .899 Modern procurement and supply chains require hybrid project management approaches (Agile + Waterfall) to adapt to VUCA (volatile, uncertain, complex, ambiguous) environments 200 3.84 1.068 Current procurement and supply chain management practices lack sufficient integration with project management, leading to misalignment and inefficiencies 200 3.51 1.260 Project procurement management requires strong leadership and clear governance structures, setting clear priorities, and ensure alignment across the organisation 200 4.01 1.000 Artificial Intelligence (AI), Internet of Things (IoT), and blockchain play a critical role in enhancing project procurement and supply chain visibility, traceability, and decision-making 200 4.01 1.000 Project management methodologies, such as Work Breakdown Structure and Critical Path Method, facilitate procurement's adaptation to rapid and unpredictable changes 200 3.51 1.385 Agile project management practices bolster procurement and supply chain resilience by allowing real-time modifications in response to demand fluctuations and disruptions 200 3.51 1.385 An integrated project procurement management framework is crucial for navigating VUCA environments, as traditional procurement and supply chain methods are inadequate on their own 200 4.01 1.000 Dynamic risk management is crucial in a VUCA environment, as traditional risk management approaches may fail to address rapid and unpredictable project procurement changes 200 3.34 1.250 Resource optimization techniques from project management, including resource leveling and dependency matrices, mitigate inefficiencies in complex, multi-stakeholder procurement and supply chains 200 3.51 1.385 Source : Bentahar & Belhadi ( 2025 ); Aalto ( 2024 ); Honkala ( 2024 ). Note : A denotes Q1-Q5, B denotes Q6-Q10, and C denotes Q11-Q15. 3.3 Multilayer Perceptron Artificial Neural Network Model The output of the MLP ANN method on the predicting project procurement management in VUCA environment was investigated in this analysis. Predictive ANNs are particularly useful in applications with a complicated mechanism. ANNs are currently gaining popularity as a solution to problems that cannot be solved with traditional methods, and they have been used successfully in a variety of medical applications. ANNs, unlike conventional spectral analysis, approaches model signals as well as generate signal classification solutions. The MLP ANN model is a nonparametric artificial neural network technique that can perform a wide range of detection and prediction tasks (). Approximately 74.5% and 25.5% of the entire dataset is used for the training and testing process, respectively, to create the MLP ANN model. The number of units in the input layer was 7, the number of units in the hidden layer was 1, the hidden layer activation function was a hyperbolic tangent, the number of units in the output layer was 1, the output layer activation function was Identity, and the error function was Sum of squares. 3.4 Data Analysis IBM SPSS Statistics 26.0 program was used for all analyzes in the study. The statistical analysis findings of the variables included in the data set are presented in Table 4 . The provided MLP neural network output offers empirical insights into how AI (specifically, Multilayer Perceptron) can address the VUCA risk mitigation in project procurement management. The MLP (Multilayer Perceptron) model analyzes how systematic frameworks (Mean = 4.01) to improve resilience, technology adoption (AI/IoT/blockchain, Mean = 4.01) for visibility, and Hybrid Agile-Waterfall approaches (Mean = 3.84) for VUCA adaptability (input variables `a` and `b`) predict outcomes (`c`), revealing. Variable `b` dominates influence (Normalized Importance = 100%) over `a` (20.4%), suggesting latent factors (e.g., leadership, governance) may outweigh observable metrics in driving procurement success. Hidden layer (hyperbolic tangent activation) captures non-linear relationships, while the identity output implies linear scaling of predictions. Model Performance - Training (SSE = 0.002) and testing (SSE = 0.001) errors indicate strong fit, and training completed instantly, suggesting efficient learning from the data. Input Layer : `a = 22.00` has the highest positive weight (0.405), implying specific procurement scenarios (e.g., high-complexity projects) significantly impact outcomes (Villena, 2019 ). `a = 19.00` shows negative influence (-0.268), possibly reflecting inefficiencies in mid-range procurement activities. Hidden Layer: Strong positive weight (1.535) for `H(1:1)` indicates effective feature transformation. Bias Terms: Output layer bias (-0.299) suggests baseline adjustments to predictions. The study shows that there is the need to prioritize `b`-like factors - Leadership, governance, and technology (aligned with descriptive stats' high-mean items) are critical drivers (Tsygankov et al., 2021 ; Mutisya, 2022 ). Optimize `a`-like variables- Address inefficiencies in mid-range procurement activities (e.g., `a = 19.00`), and leverage hybrid PM methods: The model’s non-linear handling supports Agile-Waterfall integration (Mean = 3.84 in stats). Multilayer Perception Table 4 Case Processing Summary Case Processing Summary N Percent Sample Training 149 74.5% Testing 51 25.5% Valid 200 100.0% Total 200 Table 5 Network Information Network Information Input Layer Factors 1 a Covariates 1 b Number of Units a 7 Rescaling Method for Covariates Standardized Hidden Layer(s) Number of Hidden Layers 1 Number of Units in Hidden Layer 1 a 1 Activation Function Hyperbolic tangent Output Layer Dependent Variables 1 c Number of Units 1 Rescaling Method for Scale Dependents Standardized Activation Function Identity Error Function Sum of Squares a. Excluding the bias unit Table 6: Model Summary Model Summary Training Sum of Squares Error .002 Relative Error 2.636E-5 Stopping Rule Used Training error ratio criterion (.001) achieved Training Time 0:00:00.00 Testing Sum of Squares Error .001 Relative Error 4.328E-5 Dependent Variable: c Table 7: Parameter Estimates Parameter Estimates Predictor Predicted Hidden Layer 1 Output Layer H(1:1) c Input Layer (Bias) .091 [a=5.00] .017 [a=17.00] .171 [a=19.00] -.268 [a=22.00] .405 [a=23.00] -.058 [a=25.00] .147 b 1.153 Hidden Layer 1 (Bias) -.299 H(1:1) 1.535 Table 8: Independent Variable Importance Independent Variable Importance Importance Normalized Importance a .169 20.4% b .831 100.0% 4. Discussion This study aims to predict project procurement management in VUCA environment using Multilayer Perceptron (MLP) Neural Networks. It advocates for digital procurement incentives and project procurement management and standardization. Project procurement has emerged as a prevalent corporate tactic due to intense competition (Özkan et al., 2021 ). The impact of suppliers on the success or failure of projects is substantial, as their performance influences the outcomes of the entire business endeavor (Cheng & Carrillo, 2012 ). Furthermore, choosing a suitably qualified supplier enhances stakeholders' confidence, as this is more likely to result in the attainment of project objectives. In this context, proficiency in the procurement process is crucial for attaining favorable outcomes in any project (Eriksson & Westerberg, 2011 ). Consequently, choosing the appropriate supplier for a project and assessing the supplier's performance during contract execution is crucial for achieving a favorable conclusion. Consequently, managers must focus on two critical aspects of the project procurement process: (1) supplier selection and (2) supplier evaluation. Since suppliers' performance is critical for the success of projects, their performance also critically influences the procurement process. The MLP analysis and descriptive statistics indicate that technology and leadership (`B`: Q6–Q10) are crucial in facilitating adaptive procurement outcomes (`C`: Q11–Q15), as demonstrated by the predominant normalized importance (100%) of `B` in the MLP model. High mean scores (4.01) for Q9 (leadership) and Q10 (AI/IoT) in descriptive statistics. Structural frameworks (A: Q1–Q5) are essential yet subordinate. The diminished influence (20.4%) in the MLP corresponds with moderate mean scores (3.34–3.84), indicating that frameworks alone are inadequate without the combination of technology and leadership. The hyperbolic tangent activation of the hidden layer encapsulates intricate interactions, such as the declining returns of mid-range framework stiffness at `a = 19.00`. Prevalence of `B` (Q6–Q10). Normalized Importance = 100% (compared to 20.4% for `A`). Affirms that technology integration (Q6–Q10) is the most significant predictor of adaptive procurement outcomes (`C`). The results correspond with the descriptive statistics, as questions 6 to 10 exhibit elevated means, such as 4.01 for questions 9 and 10. The hyperbolic tangent activation function captures intricate connections between structural frameworks (A, e.g., Q1–Q5) and Leadership/technology (B, e.g., Q9–Q10) through non-linear linkages. Consequently, a negative weight for `a = 19.00` (mid-range `A` values) may indicate diminishing returns from excessively restrictive frameworks. The output layer (`C`) employs an identity function, resulting in predictions that scale linearly with the outputs of the hidden layer. The substantial hidden-to-output weight (1.535) indicates that adaptive techniques (`C`) are directly influenced by altered inputs, such as hybrid PM approaches in Q11–Q15. 5. Future studies Future work would compare MLP with ReLU activation or Transformer architectures for handling survey data using python - scikitlearn. 6. Contribution to Theory, Practice, and Policy Project procurement must be resilient and sustainable to achieve long-term organizational objectives and adapt to VUCA conditions (Bag, 2025 ). The research connects theoretical project procurement management and supply chain synergy with empirical validation, providing a framework for project procurement and supply chains that are prepared for VUCA conditions (Grzybowska & Tubis, 2022 ; Huzooree & Yadav, 2025 ; Kareem, n.d.). 7. Recommendations Investing in AI/IoT tools and governance to enhance project procurement management framework is crucial for navigating VUCA environments (Akhtar, 2025 ; Ejjami & Boussalham, 2024 ). Also, it bolster project procurement and supply chain resilience by allowing real-time modifications in response to demand fluctuations and disruptions (Ivanov & Dolgui, 2021 ). Moreover, the study recommends academics to develop a unified project procurement management framework combining (systematic project procurement management framework enhances sustainability and resilience in engineering, construction, and procurement by reducing inefficiencies, providing precise information, and utilizing data analytics for proactive management, sustainable sourcing practices, and contingency plans) and (Resilient and sustainable project procurement to meet long-term organizational goals and adapt to VUCA environments. Strong leadership, clear governance structures, and the use of AI, IoT, and blockchain are crucial for improved visibility and decision-making). Declarations This study was approved by the Ethics Committee of Kwame Nkrumah University of Science and Technology - KNUST. All the written consents were signed voluntarily. References Aalto, V. (2024). The role of procurement in enhancing the project scheduling process. Akhtar, L. (2025). Procurement 4.0: Investigating AI adoption for Intelligent and Resilient Supply Chains. Álvarez-Espada, J. M., Fuentes-Bargues, J. L., Sánchez-Lite, A., & González-Gaya, C. (2024). Complexity Assessment in Projects Using Small-World Networks for Risk Factor Reduction. Buildings , 14 (12), 4065. Amirtash, P., Parchami Jalal, M., & Jelodar, M. B. (2021). Integration of project management services for International Engineering, Procurement and Construction projects. Built Environment Project and Asset Management , 11 (2), 330-349. Bag, S. (2025). Developing agile, digital, resilient and sustainable suppliers’ dynamic capability for enhanced supply chain quality: a qualitative study. The TQM Journal . Bentahar, O., & Belhadi, A. (2025, January). Integrating project management and supply chain management for resilient and sustainable operations in a VUCA world. In Supply Chain Forum: An International Journal (Vol. 26, No. 1, pp. 1-6). Taylor & Francis. Bentahar, O., & Belhadi, A. (2025, January). Integrating project management and supply chain management for resilient and sustainable operations in a VUCA world. In Supply Chain Forum: An International Journal (Vol. 26, No. 1, pp. 1-6). Taylor & Francis. Bradley, S. (2016). Cross-cultural factors impacting successful project procurement management implementations. Cheng, L. C., & Carrillo, E. E. (2012). Assessing supplier performances under partnership in project‐type procurement. Industrial Management & Data Systems , 112 (2), 290-312. de Araújo, M. C. B., Alencar, L. H., & de Miranda Mota, C. M. (2017). Project procurement management: A structured literature review. International journal of project management , 35 (3), 353-377. Dong, X., & Qiu, W. (2024). A case study on the relationship between risk assessment of scientific research projects and related factors under the Naive Bayesian algorithm. Scientific Reports , 14 (1), 8244. Ejjami, R., & Boussalham, K. (2024). Resilient supply chains in Industry 5.0: Leveraging AI for predictive maintenance and risk mitigation. International Journal For Multidisciplinary Research , 6 (4). El-Sayegh, S. M. (2008). Evaluating the effectiveness of project delivery methods. Journal of Construction Management and Economics , 23 (5), 457-465. Eriksson, P. E., & Westerberg, M. (2011). Effects of cooperative procurement procedures on construction project performance: A conceptual framework. International journal of project management , 29 (2), 197-208. Fridgeirsson, T. V., Ingason, H. T., Jonasson, H. I., & Kristjansdottir, B. H. (2021). The VUCAlity of projects: A new approach to assess a project risk in a complex world. Sustainability , 13 (7), 3808. Gomes, J., & Romão, M. (2016). Improving project success: A case study using benefits and project management. Procedia Computer Science , 100 , 489-497. Govindan, K., Jain, P., Singh, R. K., & Mishra, R. (2024). Blockchain technology as a strategic weapon to bring procurement 4.0 truly alive: Literature review and future research agenda. Transportation Research Part E: Logistics and Transportation Review , 181 , 103352. Grzybowska, K., & Tubis, A. A. (2022). Supply chain resilience in reality VUCA—An international delphi study. Sustainability , 14 (17), 10711. Gunnarsdóttir, A. Ý. (2021). An authoritative study on a new approach to enhance traditional project risk identification process in a VUCA world (Doctoral dissertation). Herold, S., Heller, J., Rozemeijer, F., & Mahr, D. (2023). Dynamic capabilities for digital procurement transformation: a systematic literature review. International Journal of Physical Distribution & Logistics Management , 53 (4), 424-447. Honkala, K. (2024). Procurement process development in a project-based company. Hussain, A., Jamil, M., Farooq, M. U., Asim, M., Rafique, M. Z., & Pruncu, C. I. (2021). Project managers’ personality and project success: Moderating role of external environmental factors. Sustainability , 13 (16), 9477. Huzooree, G., & Yadav, M. (2025). Sustainable Project Management and Organizational Resilience. In Enhancing Resilience in Business Continuity Management (pp. 137-172). IGI Global Scientific Publishing. Imoni, S., Akande, E. O., Jiya, V. H., Onuzulike, C., & Tiza, M. T. (2023). A Comprehensive Review of Engineering, Procurement, and Construction in Nigeria. Journal of Management Studies and Development , 2 (03), 226-249. Ivanov, D., & Dolgui, A. (2021). A digital supply chain twin for managing the disruption risks and resilience in the era of Industry 4.0. Production Planning & Control , 32 (9), 775-788. Kabirifar, K., & Mojtahedi, M. (2019). The impact of engineering, procurement and construction (EPC) phases on project performance: a case of large-scale residential construction project. Buildings , 9 (1), 15. Karatu, V. (2023). The Role of Digital Procurement Systems in Mitigating Project Delays (Doctoral dissertation, Institute of Accountancy Arusha (IAA)). Kareem, S. Adaptive Sustainable Supply Chains in a Volatile, Uncertain, Complex and Ambiguous (VUCA) Environment. Khairullah, N. H., Hilal, M. A., & Mohammed, A. (2022). Identification of the main causes of risks in engineering procurement construction projects. Journal of the Mechanical Behavior of Materials , 31 (1), 282-289. Latha, S. (2020). Vuca in engineering education: Enhancement of faculty competency for capacity building. Procedia Computer Science , 172 , 741-747. Mabilu, E. B. (2021). Factors causing delays in the pre-contract procurement process of electrical infrastructure projects (Doctoral dissertation). Maddi, M. S., Lorza, R. L., Benjread, S., Geragthy, J., & Davis, P. (2013). Project based learning in engineering schools: The roles of supply management, Procurement, Designers and Builders of a new product. International Journal for Cross-disciplinary Subjects in Education , 3 (2). Makudza, F., Jaravaza, D. C., Govha, T., Mukucha, P., & Saruchera, F. (2023). Enhancing supply chain agility through e-procurement in a volatile frontier market. Journal of Transport and Supply Chain Management , 17 , 847. Moon, E. (2020). Delays in Global Engineering Procurement and Construction Projects: Main Factors in Project Management. Mutisya, H. K. (2022). Procurement Governance, Integrative Supply Chain Technology, Procurement Performance And Service Delivery At State Ministries, Departments And Agencies In Kenya (Doctoral dissertation, University of Nairobi). Mwagike, L. R., & Changalima, I. A. (2022). Procurement professionals' perceptions of skills and attributes of procurement negotiators: a cross-sectional survey in Tanzania. International Journal of Public Sector Management , 35 (1), 94-109. Nissen, M. E. (2009). Procurement: process overview and emerging project management techniques. The Wiley Guide to Project Technology, Supply Chain & Procurement Management , 247. Özkan, E., Azizi, N., & Haass, O. (2021). Leveraging smart contract in project procurement through DLT to gain sustainable competitive advantages. Sustainability , 13 (23), 13380. Paarry, J. S., Sekhar, C., Balaji, P., & Sivakumar, S. (2018). Procurement practices prevalent in retail stores with special reference to fast moving consumer goods (FMCGs) in Tamil Nadu. International Journal of Horticulture , 8 . Popescu, M. C., Balas, V. E., Perescu-Popescu, L., & Mastorakis, N. (2009). Multilayer perceptron and neural networks. WSEAS Transactions on Circuits and Systems , 8 (7), 579-588. Rane, S. B., Narvel, Y. A. M., & Bhandarkar, B. M. (2020). Developing strategies to improve agility in the project procurement management (PPM) process: Perspective of business intelligence (BI). Business Process Management Journal , 26 (1), 257-286. Rivals, I., & Personnaz, L. (2003). MLPs (mono-layer polynomials and multi-layer perceptrons) for nonlinear modeling. Journal of Machine Learning Research , 3 (Mar), 1383-1398. Roumboutsos, A. B. (2010). Sustainability, social discount rates and the selection of project procurement method. International Advances in Economic Research , 16 , 165-174. Tassabehji, R., & Moorhouse, A. (2008). The changing role of procurement: Developing professional effectiveness. Journal of purchasing and supply management , 14 (1), 55-68. Tsygankov, S., Syropyatov, V., & Volchik, V. (2021). Institutional Governance of Innovations: Novel Insights of Leadership in Russian Public Procurement. Economies , 9 (4), 189. Villena, V. H. (2019). The missing link? The strategic role of procurement in building sustainable supply networks. Production and Operations Management , 28 (5), 1149-1172. WILLIS, K. G. (2010). Is all sustainable development sustainable? A cost-benefit analysis of some procurement projects. Journal of environmental assessment policy and management , 12 (03), 311-331. Zidan, A. R. A., & Hady, M. A. A. (2018). ANNs Modeling and SPSS Analysis. In Constructed Subsurface Wetlands (pp. 357-514). Apple Academic Press. Additional Declarations The authors declare no competing interests. Cite Share Download PDF Status: Posted Version 1 posted You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-6996931","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":477691608,"identity":"6e9b05de-9eaa-4d0c-9dae-58277668e063","order_by":0,"name":"Stephen Turkson","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA+klEQVRIiWNgGAWjYFACxgYwJQEiEipsQCKNBwhqOZAA1fLgTBpYhIAWIIBpYXzYdhgigE+1fPvhtscffxzOl+w/fOxBYtt5u7Xth4G21NhE49JicCax3eBAwmHL2RJp6QYJ524nbzuTCNRyLC23AZcWhsQ2CaAWAzkJHjOJhLLbyWYHgFoYGw7j1CLf/xCqhf8MUAvbuWSz8w/xa2G4AbVFmiEHqKXtgJ3ZDQK2GNwA2nIG6A3JGWlpEglnkhPMbgBtScDjF/n+9GcSFTbWBhLnDx+T/FFhZ292Pv3hgw81Nrgdhg4SwSoTiFUOAvakKB4Fo2AUjIKRAQAQkGfvxdlNmgAAAABJRU5ErkJggg==","orcid":"https://orcid.org/0000-0001-7434-5587","institution":"Centre for Educational Empowerment for Women","correspondingAuthor":true,"prefix":"","firstName":"Stephen","middleName":"","lastName":"Turkson","suffix":""},{"id":477691609,"identity":"7bd9ea32-0be0-4d57-a931-06779fdaae09","order_by":1,"name":"Patience Aboagyewaa","email":"","orcid":"https://orcid.org/0009-0005-3475-3494","institution":"Centre for Educational Empowerment for Women","correspondingAuthor":false,"prefix":"","firstName":"Patience","middleName":"","lastName":"Aboagyewaa","suffix":""}],"badges":[],"createdAt":"2025-06-28 09:43:42","currentVersionCode":1,"declarations":{"humanSubjects":true,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":true,"humanSubjectConsent":true,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-6996931/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6996931/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":85917867,"identity":"5ef0f4eb-f200-49b0-98f7-48a5009df727","added_by":"auto","created_at":"2025-07-03 07:13:57","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":40963,"visible":true,"origin":"","legend":"\u003cp\u003eUnnumbered image in the Results section.\u003c/p\u003e","description":"","filename":"Picture1.png","url":"https://assets-eu.researchsquare.com/files/rs-6996931/v1/54be0b8a5ad61e45de6cb210.png"},{"id":85919376,"identity":"1fd1611f-7400-4a60-879f-dfa304a3743a","added_by":"auto","created_at":"2025-07-03 07:37:58","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":754938,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6996931/v1/988f23f3-ea7b-4c2c-8759-b0c8068b5915.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003e\u003cstrong\u003eNeural Networks - Multilayer Perceptron inference on Project Procurement Management in VUCA environments\u003c/strong\u003e\u003c/p\u003e","fulltext":[{"header":"1. Introduction","content":"\u003cp\u003eEngineering, procurement and construction projects provide intricate and essential infrastructure and construction projects. However, these projects face multiple challenges and uncertainties (VUCA) (Kabirifar \u0026amp; Mojtahedi, \u003cspan citationid=\"CR26\" class=\"CitationRef\"\u003e2019\u003c/span\u003e; Latha, \u003cspan citationid=\"CR30\" class=\"CitationRef\"\u003e2020\u003c/span\u003e; Imoni et al., \u003cspan citationid=\"CR24\" class=\"CitationRef\"\u003e2023\u003c/span\u003e; Bentahar \u0026amp; Belhadi, \u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e2025\u003c/span\u003e). The VUCA era, characterized by volatility, uncertainty, complexity, and ambiguity, presents a challenging and unpredictable world where organizations and businesses face potential risks and challenges (Gunnarsd\u0026oacute;ttir, \u003cspan citationid=\"CR19\" class=\"CitationRef\"\u003e2021\u003c/span\u003e; Fridgeirsson et al., \u003cspan citationid=\"CR15\" class=\"CitationRef\"\u003e2021\u003c/span\u003e). VUCA characterizes the hard conditions and circumstances within which organizations function. Volatility pertains to the unpredictability and instability of change; uncertainty denotes the absence of understanding regarding future occurrences and their ramifications; and complexity involves numerous interconnected components that create an intricate network of information and processes (Makudza et al., \u003cspan citationid=\"CR33\" class=\"CitationRef\"\u003e2023\u003c/span\u003e; Dong \u0026amp; Qiu, \u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e2024\u003c/span\u003e). Ultimately, ambiguity signifies an absence of precedent for forecasting due to insufficient knowledge and comprehension of the causes, impacts, and interrelations of occurrences (\u0026Aacute;lvarez-Espada et al., \u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e2024\u003c/span\u003e). Typically, in engineering, procurement and construction projects, the widely known risks/vuca include inaccurate cost estimation for the engineering phase, imprecise time estimation for the engineering phase, deficiency of management and skilled personnel, design flaws, supplier failures, unsuitable and inadequate technical drawings, diminished design time and expedited transition to the execution phase, delays in obtaining the project's initial permits, inadequate feasibility studies, inexperienced project managers, alterations due to political events, internal policy modifications within the organization, changes to the project's scope, scarcity of essential resources, and shifts in the employer's requirements (Moon, \u003cspan citationid=\"CR34\" class=\"CitationRef\"\u003e2020\u003c/span\u003e; Mabilu, \u003cspan citationid=\"CR31\" class=\"CitationRef\"\u003e2021\u003c/span\u003e; Karatu, \u003cspan citationid=\"CR27\" class=\"CitationRef\"\u003e2023\u003c/span\u003e).\u003c/p\u003e \u003cp\u003eAccording to Gomes \u0026amp; Rom\u0026atilde;o (\u003cspan citationid=\"CR16\" class=\"CitationRef\"\u003e2016\u003c/span\u003e), projects promote organizational changes, influencing the environment and product development. However, they often fail to meet goals, with 36% of global projects considered unsuccessful. These failures cost hundreds of billions of dollars annually, not limited to specific regions or industries. Consequently, although projects initiate change, project procurement management (PPM) serves as a stabilizing force, enhancing success rates by fostering agility, collaboration, and strategic resource allocation (Govindan et al., (\u003cspan citationid=\"CR17\" class=\"CitationRef\"\u003e2024\u003c/span\u003e). Project management is intertwined with procurement, and it has also been subject to considerable transformation from very low cost to least evaluated cost procurement for social and environmental sustainability (Willis, \u003cspan citationid=\"CR47\" class=\"CitationRef\"\u003e2010\u003c/span\u003e; Roumboutsos, \u003cspan citationid=\"CR43\" class=\"CitationRef\"\u003e2010\u003c/span\u003e). Project procurement management form an important topic in current academic, business, and political debates of improving the efficiency and effectiveness of project delivery on time and within budget (El-Sayegh, \u003cspan citationid=\"CR13\" class=\"CitationRef\"\u003e2008\u003c/span\u003e; de Ara\u0026uacute;jo et al., \u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e2017\u003c/span\u003e). Procurement has undergone significant transformation since its emergence as a discipline predominantly within the manufacturing sector in the mid-twentieth century (Tassabehji \u0026amp; Moorhouse, \u003cspan citationid=\"CR44\" class=\"CitationRef\"\u003e2008\u003c/span\u003e; Rane et al., \u003cspan citationid=\"CR41\" class=\"CitationRef\"\u003e2020\u003c/span\u003e; Rane \u0026amp; Narvel, 2021). In the 1980s and 1990s, procurement procedures evolved due to globalized market demands, requiring companies to acquire various supplies like raw materials, components, and consumables (Herold et al., \u003cspan citationid=\"CR20\" class=\"CitationRef\"\u003e2023\u003c/span\u003e). Project procurement improves agility in the procurement project procurement management (PPM) process, including all organizational divisions, including sales, marketing, engineering design, and production (Nissen, \u003cspan citationid=\"CR37\" class=\"CitationRef\"\u003e2009\u003c/span\u003e; Maddi et al., \u003cspan citationid=\"CR32\" class=\"CitationRef\"\u003e2013\u003c/span\u003e; Amirtash et al., \u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e2021\u003c/span\u003e).\u003c/p\u003e \u003cp\u003eMoreover, understanding behavioural characteristics of procurement professionals on projects, influencing procurement professionals on procurement project management, conflict management, and cultural awareness deemed to be a success factor for procurement project management (Bradley, \u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e2016\u003c/span\u003e; Mwagike \u0026amp; Changalima, \u003cspan citationid=\"CR36\" class=\"CitationRef\"\u003e2022\u003c/span\u003e). Also, appropriate safeguards and coordination mechanisms to succeed on procurement works on any building or civil project(s) is also a success factor for procurement project management (Buzzetto et al., 2020; Khairullah et al., \u003cspan citationid=\"CR29\" class=\"CitationRef\"\u003e2022\u003c/span\u003e). According to Kafile (2018), project managers ought to strategically approach the procurement process to maximize the efficiency of a project by considering factors like timeline, quality of project, and budget.\u003c/p\u003e \u003cp\u003eThe present research premise is that project procurement management\u0026rsquo;s adverse environment on project success and the moderating role of the chosen management method. It assumes that globalization and rapid technological changes in the VUCA era cause changes in project environments, leading to a mismatch between management methods and project results (Kafile \u0026amp; Fore, 2018; Hussain et al., \u003cspan citationid=\"CR22\" class=\"CitationRef\"\u003e2021\u003c/span\u003e). This study utilizes Multilayer Perceptron (MLP) Neural Networks to forecast VUCA Risks in project procurement management and improve project procurement decision-making with AI-driven insights (Govindan et al., \u003cspan citationid=\"CR17\" class=\"CitationRef\"\u003e2024\u003c/span\u003e). This study theoretically enhances the literature on AI-augmented project procurement management (PPM) within the settings of engineering, procurement, and construction projects (Karatu, \u003cspan citationid=\"CR27\" class=\"CitationRef\"\u003e2023\u003c/span\u003e).\u003c/p\u003e \u003cp\u003eArtificial Neural Networks (ANNs) are computer systems designed to autonomously acquire abilities such as generating and discovering new information through learning, akin to the functions of the human brain, without external assistance (Zidan \u0026amp; Hady, \u003cspan citationid=\"CR48\" class=\"CitationRef\"\u003e2018\u003c/span\u003e). Artificial Neural Networks can model nonlinearity without requiring any assumptions or prior knowledge regarding input and output variables (Rivals \u0026amp; Personnaz, \u003cspan citationid=\"CR42\" class=\"CitationRef\"\u003e2003\u003c/span\u003e). Moreover, the Multilayer Perceptron (MLP) is among the most often employed artificial neural network models for addressing nonlinear issues. This feed-forward backpropagation network contains a minimum of one layer between the input and output layers. The weight values across the layers are adjusted to minimize the computed error during the backpropagation phase, following the assessment of the network's output and error in the forward propagation phase (Popescu et al., \u003cspan citationid=\"CR40\" class=\"CitationRef\"\u003e2009\u003c/span\u003e). This work aimed to predict project procurement management in VUCA environment using Multilayer Perceptron (MLP) Neural Networks.\u003c/p\u003e"},{"header":"2. Materials and Methods","content":"\u003cp\u003eThe study employs a survey research design method to evaluate the performance of the MLP ANN model and predict project procurement management in VUCA environment using Multilayer Perceptron (MLP) Neural Networks. The study\u0026rsquo;s population comprises ofprocurement managers and tutors, project managers and project management lecturers and students, engineering and construction professionals and experts in Ghana. Thus, the convenience sampling technique used was to sample respondents who can provide accurate responses to the questions (Paarry et al., \u003cspan citationid=\"CR39\" class=\"CitationRef\"\u003e2018\u003c/span\u003e). The questionnaire was distributed to the respondents via google forms - electronic, and each respondent was instructed to fill out the questionnaire and return it in 3 days\u0026rsquo; time or earlier. 220 questionnaires were administered electronically to the sampled respondents and 200 responses were obtained, and the analysis was conducted using the Multilayer Perceptron (MLP) Neural Networks.\u003c/p\u003e"},{"header":"3. Results","content":"\u003cdiv id=\"Sec4\" class=\"Section2\"\u003e \u003ch2\u003e3.1 Demographics\u003c/h2\u003e \u003cp\u003eFrom the Table\u0026nbsp;\u003cspan refid=\"Tab1\" class=\"InternalRef\"\u003e1\u003c/span\u003e below, the results show that respondents to the survey were mostly men. A majority (79.8%) of respondents were male and (16.3%) were female. Also, Table \u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e below show that 67 respondents were procurement professionals (32.2%) and 133 (63.9%) were Project/ Construction Managers.\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab1\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 1\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eGender\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"4\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colspan=\"4\" nameend=\"c4\" namest=\"c1\"\u003e \u003cp\u003eGender\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eFrequency\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c4\" namest=\"c3\"\u003e \u003cp\u003ePercent\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eFemale\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e \u003cp\u003e34 16.3\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"1\" nameend=\"c4\" namest=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMale\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e \u003cp\u003e166 79.8\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"1\" nameend=\"c4\" namest=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eTotal\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e \u003cp\u003e200 100.0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"1\" nameend=\"c4\" namest=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab2\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 2\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eOccupation\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"3\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colspan=\"3\" nameend=\"c3\" namest=\"c1\"\u003e \u003cp\u003eOccupation\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003ctr\u003e \u003cth align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eFrequency\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003ePercent\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eProcurement Professional\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e67\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e32.2\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eProject/ Construction Manager\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e133\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e63.9\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eTotal\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e200\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e100.0\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec5\" class=\"Section2\"\u003e \u003ch2\u003e3.2 Descriptive Statistics\u003c/h2\u003e \u003cp\u003eThe Table \u003cspan refid=\"Tab3\" class=\"InternalRef\"\u003e3\u003c/span\u003e below shows descriptive statistics (based on N\u0026thinsp;=\u0026thinsp;200 responses per item). Respondents strongly agree that a systematic procurement framework improves sustainability/resilience (Mean\u0026thinsp;=\u0026thinsp;4.01, SD\u0026thinsp;=\u0026thinsp;1.41). Leadership/governance (Mean\u0026thinsp;=\u0026thinsp;4.01, SD\u0026thinsp;=\u0026thinsp;1.00) and AI/IoT/blockchain (Mean\u0026thinsp;=\u0026thinsp;4.01, SD\u0026thinsp;=\u0026thinsp;1.00) are critical for procurement success. An integrated PM-procurement framework is essential for VUCA challenges (Mean\u0026thinsp;=\u0026thinsp;4.01, SD\u0026thinsp;=\u0026thinsp;1.00). Also, sustainability/resilience (Mean\u0026thinsp;=\u0026thinsp;3.84, SD\u0026thinsp;=\u0026thinsp;0.90\u0026ndash;1.34) and hybrid Agile-Waterfall approaches (Mean\u0026thinsp;=\u0026thinsp;3.84, SD\u0026thinsp;=\u0026thinsp;1.07) are deemed important. Current PM-SCM integration gaps (Mean\u0026thinsp;=\u0026thinsp;3.51, SD\u0026thinsp;=\u0026thinsp;1.26) and Agile practices (Mean\u0026thinsp;=\u0026thinsp;3.51, SD\u0026thinsp;=\u0026thinsp;1.39) show consensus but with higher variability. Lower Agreement were data analytics (Mean\u0026thinsp;=\u0026thinsp;3.34, SD\u0026thinsp;=\u0026thinsp;1.38) and dynamic risk management (Mean\u0026thinsp;=\u0026thinsp;3.34, SD\u0026thinsp;=\u0026thinsp;1.25) are seen as less impactful, suggesting room for improvement. The results imply that prioritizing leadership, technology (AI/IoT), and integrated frameworks are high-impact areas with broad agreement.\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab3\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 3\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eDescriptive sttistics\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"4\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colspan=\"4\" nameend=\"c4\" namest=\"c1\"\u003e \u003cp\u003eDescriptive Statistics\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eN\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eMean\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eStd. Deviation\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eA systematic project procurement management framework would significantly improve engineering, construction and procurement sustainability and resilience\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e200\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e4.01\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.412\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eA structured project procurement management framework reduces inefficiencies and coordination problems in complex engineering, construction and procurement projects\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e200\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e3.68\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.374\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eProject procurement assist scheduling and delivery of precise and prompt information, particularly about lead times, schedules, and their modifications\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e200\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e3.68\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.374\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eData analytics enables real-time insights and predictive capabilities, supporting proactive management of project procurement management activities\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e200\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e3.34\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.376\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eProject procurement management involves developing sustainable sourcing practices, diversifying suppliers, and creating contingency plans for critical supply chain nodes\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e200\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e3.84\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.343\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eEmphasizing resilience and sustainability ensures project procurement can withstand disruptions and contribute to long-term organisational goals\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e200\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e3.84\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e.899\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eModern procurement and supply chains require hybrid project management approaches (Agile\u0026thinsp;+\u0026thinsp;Waterfall) to adapt to VUCA (volatile, uncertain, complex, ambiguous) environments\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e200\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e3.84\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.068\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCurrent procurement and supply chain management practices lack sufficient integration with project management, leading to misalignment and inefficiencies\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e200\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e3.51\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.260\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eProject procurement management requires strong leadership and clear governance structures, setting clear priorities, and ensure alignment across the organisation\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e200\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e4.01\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.000\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eArtificial Intelligence (AI), Internet of Things (IoT), and blockchain play a critical role in enhancing project procurement and supply chain visibility, traceability, and decision-making\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e200\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e4.01\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.000\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eProject management methodologies, such as Work Breakdown Structure and Critical Path Method, facilitate procurement's adaptation to rapid and unpredictable changes\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e200\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e3.51\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.385\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAgile project management practices bolster procurement and supply chain resilience by allowing real-time modifications in response to demand fluctuations and disruptions\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e200\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e3.51\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.385\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAn integrated project procurement management framework is crucial for navigating VUCA environments, as traditional procurement and supply chain methods are inadequate on their own\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e200\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e4.01\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.000\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDynamic risk management is crucial in a VUCA environment, as traditional risk management approaches may fail to address rapid and unpredictable project procurement changes\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e200\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e3.34\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.250\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eResource optimization techniques from project management, including resource leveling and dependency matrices, mitigate inefficiencies in complex, multi-stakeholder procurement and supply chains\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e200\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e3.51\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.385\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003e \u003cstrong\u003eSource\u003c/strong\u003e: Bentahar \u0026amp; Belhadi (\u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e2025\u003c/span\u003e); Aalto (\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e2024\u003c/span\u003e); Honkala (\u003cspan citationid=\"CR21\" class=\"CitationRef\"\u003e2024\u003c/span\u003e).\u003c/p\u003e \u003cp\u003e \u003cstrong\u003eNote\u003c/strong\u003e: A denotes Q1-Q5, B denotes Q6-Q10, and C denotes Q11-Q15.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec6\" class=\"Section2\"\u003e \u003ch2\u003e3.3 Multilayer Perceptron Artificial Neural Network Model\u003c/h2\u003e \u003cp\u003eThe output of the MLP ANN method on the predicting project procurement management in VUCA environment was investigated in this analysis. Predictive ANNs are particularly useful in applications with a complicated mechanism. ANNs are currently gaining popularity as a solution to problems that cannot be solved with traditional methods, and they have been used successfully in a variety of medical applications. ANNs, unlike conventional spectral analysis, approaches model signals as well as generate signal classification solutions. The MLP ANN model is a nonparametric artificial neural network technique that can perform a wide range of detection and prediction tasks (). Approximately 74.5% and 25.5% of the entire dataset is used for the training and testing process, respectively, to create the MLP ANN model. The number of units in the input layer was 7, the number of units in the hidden layer was 1, the hidden layer activation function was a hyperbolic tangent, the number of units in the output layer was 1, the output layer activation function was Identity, and the error function was Sum of squares.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec7\" class=\"Section2\"\u003e \u003ch2\u003e3.4 Data Analysis\u003c/h2\u003e \u003cp\u003eIBM SPSS Statistics 26.0 program was used for all analyzes in the study. The statistical analysis findings of the variables included in the data set are presented in Table\u0026nbsp;\u003cspan refid=\"Tab4\" class=\"InternalRef\"\u003e4\u003c/span\u003e. The provided MLP neural network output offers empirical insights into how AI (specifically, Multilayer Perceptron) can address the VUCA risk mitigation in project procurement management. The MLP (Multilayer Perceptron) model analyzes how systematic frameworks (Mean\u0026thinsp;=\u0026thinsp;4.01) to improve resilience, technology adoption (AI/IoT/blockchain, Mean\u0026thinsp;=\u0026thinsp;4.01) for visibility, and Hybrid Agile-Waterfall approaches (Mean\u0026thinsp;=\u0026thinsp;3.84) for VUCA adaptability (input variables `a` and `b`) predict outcomes (`c`), revealing. Variable `b` dominates influence (Normalized Importance\u0026thinsp;=\u0026thinsp;100%) over `a` (20.4%), suggesting latent factors (e.g., leadership, governance) may outweigh observable metrics in driving procurement success. Hidden layer (hyperbolic tangent activation) captures non-linear relationships, while the identity output implies linear scaling of predictions.\u003c/p\u003e \u003cp\u003e \u003cb\u003eModel Performance -\u003c/b\u003e Training (SSE\u0026thinsp;=\u0026thinsp;0.002) and testing (SSE\u0026thinsp;=\u0026thinsp;0.001) errors indicate strong fit, and training completed instantly, suggesting efficient learning from the data.\u003c/p\u003e \u003cp\u003e \u003cspan type=\"ItalicUnderline\" class=\"ItalicUnderline\" name=\"Emphasis\"\u003eInput Layer\u003c/span\u003e:\u003c/p\u003e \u003cp\u003e`a\u0026thinsp;=\u0026thinsp;22.00` has the highest positive weight (0.405), implying specific procurement scenarios (e.g., high-complexity projects) significantly impact outcomes (Villena, \u003cspan citationid=\"CR46\" class=\"CitationRef\"\u003e2019\u003c/span\u003e). `a\u0026thinsp;=\u0026thinsp;19.00` shows negative influence (-0.268), possibly reflecting inefficiencies in mid-range procurement activities. Hidden Layer: Strong positive weight (1.535) for `H(1:1)` indicates effective feature transformation. Bias Terms: Output layer bias (-0.299) suggests baseline adjustments to predictions. The study shows that there is the need to prioritize `b`-like factors - Leadership, governance, and technology (aligned with descriptive stats' high-mean items) are critical drivers (Tsygankov et al., \u003cspan citationid=\"CR45\" class=\"CitationRef\"\u003e2021\u003c/span\u003e; Mutisya, \u003cspan citationid=\"CR35\" class=\"CitationRef\"\u003e2022\u003c/span\u003e). Optimize `a`-like variables- Address inefficiencies in mid-range procurement activities (e.g., `a\u0026thinsp;=\u0026thinsp;19.00`), and leverage hybrid PM methods: The model\u0026rsquo;s non-linear handling supports Agile-Waterfall integration (Mean\u0026thinsp;=\u0026thinsp;3.84 in stats).\u003c/p\u003e \u003cp\u003e \u003cb\u003eMultilayer Perception\u003c/b\u003e \u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab4\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 4\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eCase Processing Summary\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"4\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colspan=\"4\" nameend=\"c4\" namest=\"c1\"\u003e \u003cp\u003eCase Processing Summary\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eN\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003ePercent\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003eSample\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eTraining\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e149\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e74.5%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eTesting\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e51\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e25.5%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eValid\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e200\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e100.0%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eTotal\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e200\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab5\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 5\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eNetwork Information\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"4\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colspan=\"4\" nameend=\"c4\" namest=\"c1\"\u003e \u003cp\u003eNetwork Information\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"3\" rowspan=\"4\"\u003e \u003cp\u003eInput Layer\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eFactors\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003ea\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eCovariates\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eb\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e \u003cp\u003eNumber of Units\u003csup\u003ea\u003c/sup\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e7\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e \u003cp\u003eRescaling Method for Covariates\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eStandardized\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"2\" rowspan=\"3\"\u003e \u003cp\u003eHidden Layer(s)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e \u003cp\u003eNumber of Hidden Layers\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e \u003cp\u003eNumber of Units in Hidden Layer 1\u003csup\u003ea\u003c/sup\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e \u003cp\u003eActivation Function\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eHyperbolic tangent\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"4\" rowspan=\"5\"\u003e \u003cp\u003eOutput Layer\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eDependent Variables\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003ec\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e \u003cp\u003eNumber of Units\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e \u003cp\u003eRescaling Method for Scale Dependents\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eStandardized\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e \u003cp\u003eActivation Function\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eIdentity\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e \u003cp\u003eError Function\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eSum of Squares\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"4\" nameend=\"c4\" namest=\"c1\"\u003e \u003cp\u003ea. Excluding the bias unit\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003c/br\u003e\n\u003cp\u003e\u003cstrong\u003eTable 6:\u0026nbsp;\u003c/strong\u003e\u003cstrong\u003eModel Summary\u003c/strong\u003e\u003c/p\u003e\n\u003ctable border=\"1\" cellspacing=\"0\" cellpadding=\"0\" width=\"611\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd colspan=\"3\" style=\"width: 611px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eModel Summary\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd rowspan=\"4\" valign=\"top\" style=\"width: 129px;\"\u003e\n \u003cp\u003eTraining\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 279px;\"\u003e\n \u003cp\u003eSum of Squares Error\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 202px;\"\u003e\n \u003cp\u003e.002\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 279px;\"\u003e\n \u003cp\u003eRelative Error\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 202px;\"\u003e\n \u003cp\u003e2.636E-5\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 279px;\"\u003e\n \u003cp\u003eStopping Rule Used\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 202px;\"\u003e\n \u003cp\u003eTraining error ratio criterion (.001) achieved\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 279px;\"\u003e\n \u003cp\u003eTraining Time\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 202px;\"\u003e\n \u003cp\u003e0:00:00.00\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd rowspan=\"2\" valign=\"top\" style=\"width: 129px;\"\u003e\n \u003cp\u003eTesting\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 279px;\"\u003e\n \u003cp\u003eSum of Squares Error\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 202px;\"\u003e\n \u003cp\u003e.001\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 279px;\"\u003e\n \u003cp\u003eRelative Error\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 202px;\"\u003e\n \u003cp\u003e4.328E-5\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd colspan=\"3\" valign=\"top\" style=\"width: 611px;\"\u003e\n \u003cp\u003eDependent Variable: c\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e\n\u003cp\u003e\u003cbr\u003e\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eTable 7:\u0026nbsp;\u003c/strong\u003e\u003cstrong\u003eParameter Estimates\u003c/strong\u003e\u003c/p\u003e\n\u003ctable border=\"1\" cellspacing=\"0\" cellpadding=\"0\" width=\"607\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd colspan=\"4\" style=\"width: 607px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eParameter Estimates\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd colspan=\"2\" rowspan=\"3\" valign=\"bottom\" style=\"width: 293px;\"\u003e\n \u003cp\u003ePredictor\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" valign=\"bottom\" style=\"width: 314px;\"\u003e\n \u003cp\u003ePredicted\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"bottom\" style=\"width: 164px;\"\u003e\n \u003cp\u003eHidden Layer 1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 150px;\"\u003e\n \u003cp\u003eOutput Layer\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"bottom\" style=\"width: 164px;\"\u003e\n \u003cp\u003eH(1:1)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 150px;\"\u003e\n \u003cp\u003ec\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd rowspan=\"8\" valign=\"top\" style=\"width: 174px;\"\u003e\n \u003cp\u003eInput Layer\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 119px;\"\u003e\n \u003cp\u003e(Bias)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 164px;\"\u003e\n \u003cp\u003e.091\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 150px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 119px;\"\u003e\n \u003cp\u003e[a=5.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 164px;\"\u003e\n \u003cp\u003e.017\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 150px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 119px;\"\u003e\n \u003cp\u003e[a=17.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 164px;\"\u003e\n \u003cp\u003e.171\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 150px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 119px;\"\u003e\n \u003cp\u003e[a=19.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 164px;\"\u003e\n \u003cp\u003e-.268\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 150px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 119px;\"\u003e\n \u003cp\u003e[a=22.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 164px;\"\u003e\n \u003cp\u003e.405\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 150px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 119px;\"\u003e\n \u003cp\u003e[a=23.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 164px;\"\u003e\n \u003cp\u003e-.058\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 150px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 119px;\"\u003e\n \u003cp\u003e[a=25.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 164px;\"\u003e\n \u003cp\u003e.147\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 150px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 119px;\"\u003e\n \u003cp\u003eb\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 164px;\"\u003e\n \u003cp\u003e1.153\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 150px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd rowspan=\"2\" valign=\"top\" style=\"width: 174px;\"\u003e\n \u003cp\u003eHidden Layer 1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 119px;\"\u003e\n \u003cp\u003e(Bias)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 164px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 150px;\"\u003e\n \u003cp\u003e-.299\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 119px;\"\u003e\n \u003cp\u003eH(1:1)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 164px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 150px;\"\u003e\n \u003cp\u003e1.535\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e\n\u003cp\u003e\u003cbr\u003e\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eTable 8:\u0026nbsp;\u003c/strong\u003e\u003cstrong\u003eIndependent Variable Importance\u003c/strong\u003e\u003c/p\u003e\n\u003ctable border=\"1\" cellspacing=\"0\" cellpadding=\"0\" width=\"603\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd colspan=\"3\" style=\"width: 603px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eIndependent Variable Importance\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"bottom\" style=\"width: 129px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 217px;\"\u003e\n \u003cp\u003eImportance\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 257px;\"\u003e\n \u003cp\u003eNormalized Importance\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 129px;\"\u003e\n \u003cp\u003ea\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 217px;\"\u003e\n \u003cp\u003e.169\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 257px;\"\u003e\n \u003cp\u003e20.4%\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 129px;\"\u003e\n \u003cp\u003eb\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 217px;\"\u003e\n \u003cp\u003e.831\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 257px;\"\u003e\n \u003cp\u003e100.0%\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e"},{"header":"4. Discussion","content":"\u003cp\u003eThis study aims to predict project procurement management in VUCA environment using Multilayer Perceptron (MLP) Neural Networks. It advocates for digital procurement incentives and project procurement management and standardization. Project procurement has emerged as a prevalent corporate tactic due to intense competition (\u0026Ouml;zkan et al., \u003cspan citationid=\"CR38\" class=\"CitationRef\"\u003e2021\u003c/span\u003e). The impact of suppliers on the success or failure of projects is substantial, as their performance influences the outcomes of the entire business endeavor (Cheng \u0026amp; Carrillo, \u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e2012\u003c/span\u003e). Furthermore, choosing a suitably qualified supplier enhances stakeholders' confidence, as this is more likely to result in the attainment of project objectives. In this context, proficiency in the procurement process is crucial for attaining favorable outcomes in any project (Eriksson \u0026amp; Westerberg, \u003cspan citationid=\"CR14\" class=\"CitationRef\"\u003e2011\u003c/span\u003e). Consequently, choosing the appropriate supplier for a project and assessing the supplier's performance during contract execution is crucial for achieving a favorable conclusion. Consequently, managers must focus on two critical aspects of the project procurement process: (1) supplier selection and (2) supplier evaluation. Since suppliers' performance is critical for the success of projects, their performance also critically influences the procurement process.\u003c/p\u003e \u003cp\u003eThe MLP analysis and descriptive statistics indicate that technology and leadership (`B`: Q6\u0026ndash;Q10) are crucial in facilitating adaptive procurement outcomes (`C`: Q11\u0026ndash;Q15), as demonstrated by the predominant normalized importance (100%) of `B` in the MLP model. High mean scores (4.01) for Q9 (leadership) and Q10 (AI/IoT) in descriptive statistics. Structural frameworks (A: Q1\u0026ndash;Q5) are essential yet subordinate. The diminished influence (20.4%) in the MLP corresponds with moderate mean scores (3.34\u0026ndash;3.84), indicating that frameworks alone are inadequate without the combination of technology and leadership. The hyperbolic tangent activation of the hidden layer encapsulates intricate interactions, such as the declining returns of mid-range framework stiffness at `a\u0026thinsp;=\u0026thinsp;19.00`. Prevalence of `B` (Q6\u0026ndash;Q10). Normalized Importance\u0026thinsp;=\u0026thinsp;100% (compared to 20.4% for `A`). Affirms that technology integration (Q6\u0026ndash;Q10) is the most significant predictor of adaptive procurement outcomes (`C`). The results correspond with the descriptive statistics, as questions 6 to 10 exhibit elevated means, such as 4.01 for questions 9 and 10. The hyperbolic tangent activation function captures intricate connections between structural frameworks (A, e.g., Q1\u0026ndash;Q5) and Leadership/technology (B, e.g., Q9\u0026ndash;Q10) through non-linear linkages. Consequently, a negative weight for `a\u0026thinsp;=\u0026thinsp;19.00` (mid-range `A` values) may indicate diminishing returns from excessively restrictive frameworks. The output layer (`C`) employs an identity function, resulting in predictions that scale linearly with the outputs of the hidden layer. The substantial hidden-to-output weight (1.535) indicates that adaptive techniques (`C`) are directly influenced by altered inputs, such as hybrid PM approaches in Q11\u0026ndash;Q15.\u003c/p\u003e"},{"header":"5. Future studies","content":"\u003cp\u003eFuture work would compare MLP with ReLU activation or Transformer architectures for handling survey data using python - scikitlearn.\u003c/p\u003e"},{"header":"6. Contribution to Theory, Practice, and Policy","content":"\u003cp\u003eProject procurement must be resilient and sustainable to achieve long-term organizational objectives and adapt to VUCA conditions (Bag, \u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e2025\u003c/span\u003e). The research connects theoretical project procurement management and supply chain synergy with empirical validation, providing a framework for project procurement and supply chains that are prepared for VUCA conditions (Grzybowska \u0026amp; Tubis, \u003cspan citationid=\"CR18\" class=\"CitationRef\"\u003e2022\u003c/span\u003e; Huzooree \u0026amp; Yadav, \u003cspan citationid=\"CR23\" class=\"CitationRef\"\u003e2025\u003c/span\u003e; Kareem, n.d.).\u003c/p\u003e"},{"header":"7. Recommendations","content":"\u003cp\u003eInvesting in AI/IoT tools and governance to enhance project procurement management framework is crucial for navigating VUCA environments (Akhtar, \u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2025\u003c/span\u003e; Ejjami \u0026amp; Boussalham, \u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e2024\u003c/span\u003e). Also, it bolster project procurement and supply chain resilience by allowing real-time modifications in response to demand fluctuations and disruptions (Ivanov \u0026amp; Dolgui, \u003cspan citationid=\"CR25\" class=\"CitationRef\"\u003e2021\u003c/span\u003e). Moreover, the study recommends academics to develop a unified project procurement management framework combining (systematic project procurement management framework enhances sustainability and resilience in engineering, construction, and procurement by reducing inefficiencies, providing precise information, and utilizing data analytics for proactive management, sustainable sourcing practices, and contingency plans) and (Resilient and sustainable project procurement to meet long-term organizational goals and adapt to VUCA environments. Strong leadership, clear governance structures, and the use of AI, IoT, and blockchain are crucial for improved visibility and decision-making).\u003c/p\u003e"},{"header":"Declarations","content":"\u003cp\u003eThis study was approved by the Ethics Committee of Kwame Nkrumah University of Science and Technology - KNUST. All the written consents were signed voluntarily.\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\n\u003cli\u003eAalto, V. (2024). The role of procurement in enhancing the project scheduling process.\u003c/li\u003e\n\u003cli\u003eAkhtar, L. (2025). Procurement 4.0: Investigating AI adoption for Intelligent and Resilient Supply Chains.\u003c/li\u003e\n\u003cli\u003e\u0026Aacute;lvarez-Espada, J. M., Fuentes-Bargues, J. L., S\u0026aacute;nchez-Lite, A., \u0026amp; Gonz\u0026aacute;lez-Gaya, C. (2024). Complexity Assessment in Projects Using Small-World Networks for Risk Factor Reduction. \u003cem\u003eBuildings\u003c/em\u003e, \u003cem\u003e14\u003c/em\u003e(12), 4065.\u003c/li\u003e\n\u003cli\u003eAmirtash, P., Parchami Jalal, M., \u0026amp; Jelodar, M. B. (2021). Integration of project management services for International Engineering, Procurement and Construction projects. \u003cem\u003eBuilt Environment Project and Asset Management\u003c/em\u003e, \u003cem\u003e11\u003c/em\u003e(2), 330-349.\u003c/li\u003e\n\u003cli\u003eBag, S. (2025). Developing agile, digital, resilient and sustainable suppliers\u0026rsquo; dynamic capability for enhanced supply chain quality: a qualitative study. \u003cem\u003eThe TQM Journal\u003c/em\u003e.\u003c/li\u003e\n\u003cli\u003eBentahar, O., \u0026amp; Belhadi, A. (2025, January). Integrating project management and supply chain management for resilient and sustainable operations in a VUCA world. In \u003cem\u003eSupply Chain Forum: An International Journal\u003c/em\u003e (Vol. 26, No. 1, pp. 1-6). Taylor \u0026amp; Francis.\u003c/li\u003e\n\u003cli\u003eBentahar, O., \u0026amp; Belhadi, A. (2025, January). Integrating project management and supply chain management for resilient and sustainable operations in a VUCA world. In \u003cem\u003eSupply Chain Forum: An International Journal\u003c/em\u003e (Vol. 26, No. 1, pp. 1-6). Taylor \u0026amp; Francis.\u003c/li\u003e\n\u003cli\u003eBradley, S. (2016). Cross-cultural factors impacting successful project procurement management implementations.\u003c/li\u003e\n\u003cli\u003eCheng, L. C., \u0026amp; Carrillo, E. E. (2012). Assessing supplier performances under partnership in project‐type procurement. \u003cem\u003eIndustrial Management \u0026amp; Data Systems\u003c/em\u003e, \u003cem\u003e112\u003c/em\u003e(2), 290-312.\u003c/li\u003e\n\u003cli\u003ede Ara\u0026uacute;jo, M. C. B., Alencar, L. H., \u0026amp; de Miranda Mota, C. M. (2017). Project procurement management: A structured literature review. \u003cem\u003eInternational journal of project management\u003c/em\u003e, \u003cem\u003e35\u003c/em\u003e(3), 353-377.\u003c/li\u003e\n\u003cli\u003eDong, X., \u0026amp; Qiu, W. (2024). A case study on the relationship between risk assessment of scientific research projects and related factors under the Naive Bayesian algorithm. \u003cem\u003eScientific Reports\u003c/em\u003e, \u003cem\u003e14\u003c/em\u003e(1), 8244.\u003c/li\u003e\n\u003cli\u003eEjjami, R., \u0026amp; Boussalham, K. (2024). Resilient supply chains in Industry 5.0: Leveraging AI for predictive maintenance and risk mitigation. \u003cem\u003eInternational Journal For Multidisciplinary Research\u003c/em\u003e, \u003cem\u003e6\u003c/em\u003e(4).\u003c/li\u003e\n\u003cli\u003eEl-Sayegh, S. M. (2008). Evaluating the effectiveness of project delivery methods. \u003cem\u003eJournal of Construction Management and Economics\u003c/em\u003e, \u003cem\u003e23\u003c/em\u003e(5), 457-465.\u003c/li\u003e\n\u003cli\u003eEriksson, P. E., \u0026amp; Westerberg, M. (2011). Effects of cooperative procurement procedures on construction project performance: A conceptual framework. \u003cem\u003eInternational journal of project management\u003c/em\u003e, \u003cem\u003e29\u003c/em\u003e(2), 197-208.\u003c/li\u003e\n\u003cli\u003eFridgeirsson, T. V., Ingason, H. T., Jonasson, H. I., \u0026amp; Kristjansdottir, B. H. (2021). The VUCAlity of projects: A new approach to assess a project risk in a complex world. \u003cem\u003eSustainability\u003c/em\u003e, \u003cem\u003e13\u003c/em\u003e(7), 3808.\u003c/li\u003e\n\u003cli\u003eGomes, J., \u0026amp; Rom\u0026atilde;o, M. (2016). Improving project success: A case study using benefits and project management. \u003cem\u003eProcedia Computer Science\u003c/em\u003e, \u003cem\u003e100\u003c/em\u003e, 489-497.\u003c/li\u003e\n\u003cli\u003eGovindan, K., Jain, P., Singh, R. K., \u0026amp; Mishra, R. (2024). Blockchain technology as a strategic weapon to bring procurement 4.0 truly alive: Literature review and future research agenda. \u003cem\u003eTransportation Research Part E: Logistics and Transportation Review\u003c/em\u003e, \u003cem\u003e181\u003c/em\u003e, 103352.\u003c/li\u003e\n\u003cli\u003eGrzybowska, K., \u0026amp; Tubis, A. A. (2022). Supply chain resilience in reality VUCA\u0026mdash;An international delphi study. \u003cem\u003eSustainability\u003c/em\u003e, \u003cem\u003e14\u003c/em\u003e(17), 10711.\u003c/li\u003e\n\u003cli\u003eGunnarsd\u0026oacute;ttir, A. \u0026Yacute;. (2021). \u003cem\u003eAn authoritative study on a new approach to enhance traditional project risk identification process in a VUCA world\u003c/em\u003e (Doctoral dissertation).\u003c/li\u003e\n\u003cli\u003eHerold, S., Heller, J., Rozemeijer, F., \u0026amp; Mahr, D. (2023). Dynamic capabilities for digital procurement transformation: a systematic literature review. \u003cem\u003eInternational Journal of Physical Distribution \u0026amp; Logistics Management\u003c/em\u003e, \u003cem\u003e53\u003c/em\u003e(4), 424-447.\u003c/li\u003e\n\u003cli\u003eHonkala, K. (2024). Procurement process development in a project-based company.\u003c/li\u003e\n\u003cli\u003eHussain, A., Jamil, M., Farooq, M. U., Asim, M., Rafique, M. Z., \u0026amp; Pruncu, C. I. (2021). Project managers\u0026rsquo; personality and project success: Moderating role of external environmental factors. \u003cem\u003eSustainability\u003c/em\u003e, \u003cem\u003e13\u003c/em\u003e(16), 9477.\u003c/li\u003e\n\u003cli\u003eHuzooree, G., \u0026amp; Yadav, M. (2025). Sustainable Project Management and Organizational Resilience. In \u003cem\u003eEnhancing Resilience in Business Continuity Management\u003c/em\u003e (pp. 137-172). IGI Global Scientific Publishing.\u003c/li\u003e\n\u003cli\u003eImoni, S., Akande, E. O., Jiya, V. H., Onuzulike, C., \u0026amp; Tiza, M. T. (2023). A Comprehensive Review of Engineering, Procurement, and Construction in Nigeria. \u003cem\u003eJournal of Management Studies and Development\u003c/em\u003e, \u003cem\u003e2\u003c/em\u003e(03), 226-249.\u003c/li\u003e\n\u003cli\u003eIvanov, D., \u0026amp; Dolgui, A. (2021). A digital supply chain twin for managing the disruption risks and resilience in the era of Industry 4.0. \u003cem\u003eProduction Planning \u0026amp; Control\u003c/em\u003e, \u003cem\u003e32\u003c/em\u003e(9), 775-788.\u003c/li\u003e\n\u003cli\u003eKabirifar, K., \u0026amp; Mojtahedi, M. (2019). The impact of engineering, procurement and construction (EPC) phases on project performance: a case of large-scale residential construction project. \u003cem\u003eBuildings\u003c/em\u003e, \u003cem\u003e9\u003c/em\u003e(1), 15.\u003c/li\u003e\n\u003cli\u003eKaratu, V. (2023). \u003cem\u003eThe Role of Digital Procurement Systems in Mitigating Project Delays\u003c/em\u003e (Doctoral dissertation, Institute of Accountancy Arusha (IAA)).\u003c/li\u003e\n\u003cli\u003eKareem, S. Adaptive Sustainable Supply Chains in a Volatile, Uncertain, Complex and Ambiguous (VUCA) Environment.\u003c/li\u003e\n\u003cli\u003eKhairullah, N. H., Hilal, M. A., \u0026amp; Mohammed, A. (2022). Identification of the main causes of risks in engineering procurement construction projects. \u003cem\u003eJournal of the Mechanical Behavior of Materials\u003c/em\u003e, \u003cem\u003e31\u003c/em\u003e(1), 282-289.\u003c/li\u003e\n\u003cli\u003eLatha, S. (2020). Vuca in engineering education: Enhancement of faculty competency for capacity building. \u003cem\u003eProcedia Computer Science\u003c/em\u003e, \u003cem\u003e172\u003c/em\u003e, 741-747.\u003c/li\u003e\n\u003cli\u003eMabilu, E. B. (2021). \u003cem\u003eFactors causing delays in the pre-contract procurement process of electrical infrastructure projects\u003c/em\u003e (Doctoral dissertation).\u003c/li\u003e\n\u003cli\u003eMaddi, M. S., Lorza, R. L., Benjread, S., Geragthy, J., \u0026amp; Davis, P. (2013). Project based learning in engineering schools: The roles of supply management, Procurement, Designers and Builders of a new product. \u003cem\u003eInternational Journal for Cross-disciplinary Subjects in Education\u003c/em\u003e, \u003cem\u003e3\u003c/em\u003e(2).\u003c/li\u003e\n\u003cli\u003eMakudza, F., Jaravaza, D. C., Govha, T., Mukucha, P., \u0026amp; Saruchera, F. (2023). Enhancing supply chain agility through e-procurement in a volatile frontier market. \u003cem\u003eJournal of Transport and Supply Chain Management\u003c/em\u003e, \u003cem\u003e17\u003c/em\u003e, 847.\u003c/li\u003e\n\u003cli\u003eMoon, E. (2020). Delays in Global Engineering Procurement and Construction Projects: Main Factors in Project Management.\u003c/li\u003e\n\u003cli\u003eMutisya, H. K. (2022). \u003cem\u003eProcurement Governance, Integrative Supply Chain Technology, Procurement Performance And Service Delivery At State Ministries, Departments And Agencies In Kenya\u003c/em\u003e (Doctoral dissertation, University of Nairobi).\u003c/li\u003e\n\u003cli\u003eMwagike, L. R., \u0026amp; Changalima, I. A. (2022). Procurement professionals\u0026apos; perceptions of skills and attributes of procurement negotiators: a cross-sectional survey in Tanzania. \u003cem\u003eInternational Journal of Public Sector Management\u003c/em\u003e, \u003cem\u003e35\u003c/em\u003e(1), 94-109.\u003c/li\u003e\n\u003cli\u003eNissen, M. E. (2009). Procurement: process overview and emerging project management techniques. \u003cem\u003eThe Wiley Guide to Project Technology, Supply Chain \u0026amp; Procurement Management\u003c/em\u003e, 247.\u003c/li\u003e\n\u003cli\u003e\u0026Ouml;zkan, E., Azizi, N., \u0026amp; Haass, O. (2021). Leveraging smart contract in project procurement through DLT to gain sustainable competitive advantages. \u003cem\u003eSustainability\u003c/em\u003e, \u003cem\u003e13\u003c/em\u003e(23), 13380.\u003c/li\u003e\n\u003cli\u003ePaarry, J. S., Sekhar, C., Balaji, P., \u0026amp; Sivakumar, S. (2018). Procurement practices prevalent in retail stores with special reference to fast moving consumer goods (FMCGs) in Tamil Nadu. \u003cem\u003eInternational Journal of Horticulture\u003c/em\u003e, \u003cem\u003e8\u003c/em\u003e.\u003c/li\u003e\n\u003cli\u003ePopescu, M. C., Balas, V. E., Perescu-Popescu, L., \u0026amp; Mastorakis, N. (2009). Multilayer perceptron and neural networks. \u003cem\u003eWSEAS Transactions on Circuits and Systems\u003c/em\u003e, \u003cem\u003e8\u003c/em\u003e(7), 579-588.\u003c/li\u003e\n\u003cli\u003eRane, S. B., Narvel, Y. A. M., \u0026amp; Bhandarkar, B. M. (2020). Developing strategies to improve agility in the project procurement management (PPM) process: Perspective of business intelligence (BI). \u003cem\u003eBusiness Process Management Journal\u003c/em\u003e, \u003cem\u003e26\u003c/em\u003e(1), 257-286.\u003c/li\u003e\n\u003cli\u003eRivals, I., \u0026amp; Personnaz, L. (2003). MLPs (mono-layer polynomials and multi-layer perceptrons) for nonlinear modeling. \u003cem\u003eJournal of Machine Learning Research\u003c/em\u003e, \u003cem\u003e3\u003c/em\u003e(Mar), 1383-1398.\u003c/li\u003e\n\u003cli\u003eRoumboutsos, A. B. (2010). Sustainability, social discount rates and the selection of project procurement method. \u003cem\u003eInternational Advances in Economic Research\u003c/em\u003e, \u003cem\u003e16\u003c/em\u003e, 165-174.\u003c/li\u003e\n\u003cli\u003eTassabehji, R., \u0026amp; Moorhouse, A. (2008). The changing role of procurement: Developing professional effectiveness. \u003cem\u003eJournal of purchasing and supply management\u003c/em\u003e, \u003cem\u003e14\u003c/em\u003e(1), 55-68.\u003c/li\u003e\n\u003cli\u003eTsygankov, S., Syropyatov, V., \u0026amp; Volchik, V. (2021). Institutional Governance of Innovations: Novel Insights of Leadership in Russian Public Procurement. \u003cem\u003eEconomies\u003c/em\u003e, \u003cem\u003e9\u003c/em\u003e(4), 189.\u003c/li\u003e\n\u003cli\u003eVillena, V. H. (2019). The missing link? The strategic role of procurement in building sustainable supply networks. \u003cem\u003eProduction and Operations Management\u003c/em\u003e, \u003cem\u003e28\u003c/em\u003e(5), 1149-1172.\u003c/li\u003e\n\u003cli\u003eWILLIS, K. G. (2010). Is all sustainable development sustainable? A cost-benefit analysis of some procurement projects. \u003cem\u003eJournal of environmental assessment policy and management\u003c/em\u003e, \u003cem\u003e12\u003c/em\u003e(03), 311-331.\u003c/li\u003e\n\u003cli\u003eZidan, A. R. A., \u0026amp; Hady, M. A. A. (2018). ANNs Modeling and SPSS Analysis. In \u003cem\u003eConstructed Subsurface Wetlands\u003c/em\u003e (pp. 357-514). Apple Academic Press.\u003c/li\u003e\n\u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":" Neural Networks - Multilayer Perceptron, Project Procurement Management, VUCA environments","lastPublishedDoi":"10.21203/rs.3.rs-6996931/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6996931/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eEngineering, procurement and construction\u0026nbsp;projects provide intricate and essential infrastructure and construction projects. Projects initiate change, project procurement management (PPM) serves as a stabilizing force, enhancing success rates by fostering\u0026nbsp;agility, collaboration, and strategic resource allocation. This study utilizes Multilayer Perceptron (MLP) Neural Networks to forecast VUCA Risks in project procurement management and improve project procurement decision-making with AI-driven insight. The study employs a survey research design method to evaluate the performance of the MLP ANN model and predict project procurement management in VUCA environment using Multilayer Perceptron (MLP) Neural Networks. Findings show that a\u0026nbsp;systematic procurement framework improves sustainability/resilience (Mean=4.01, SD=1.41). \u0026nbsp;Leadership/governance (Mean=4.01, SD=1.00) and AI/IoT/blockchain (Mean=4.01, SD=1.00) are critical for procurement success. Also, approximately 74.5% and 25.5% of the entire dataset is used for the training and testing process, respectively, to create the MLP ANN model. The number of units in the input layer was 7, the number of units in the hidden layer was 1, the hidden layer activation function was a hyperbolic tangent, the number of units in the output layer was 1, the output layer activation function was Identity, and the error function was\u0026nbsp;Sum of squares.\u003c/p\u003e","manuscriptTitle":"Neural Networks - Multilayer Perceptron inference on Project Procurement Management in VUCA environments","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-07-03 07:13:53","doi":"10.21203/rs.3.rs-6996931/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"8ad80027-634b-4541-aed3-3ccf3c781cad","owner":[],"postedDate":"July 3rd, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":50727071,"name":"Development Economics"}],"tags":[],"updatedAt":"2025-07-03T07:13:53+00:00","versionOfRecord":[],"versionCreatedAt":"2025-07-03 07:13:53","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6996931","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6996931","identity":"rs-6996931","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}