The Impact of Machine Learning on Business Productivity: A Comprehensive Study within the Quality 5.0 Framework

The Impact of Machine Learning on Business Productivity: A Comprehensive Study within the Quality 5.0 Framework | 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 The Impact of Machine Learning on Business Productivity: A Comprehensive Study within the Quality 5.0 Framework Islam Gad, Mohamed Mahmoud, Iman Nassef This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7839321/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 The data-insight gap is persistent among Small and Medium Enterprises (SMEs): most of them generate mass volumes of data about their operations and customers, but fail to use it analytically and convert to actionable intelligence. SMEs of Saudi Arabia, this paper meets this challenge by formulating and discussing a portfolio of four low-code machine-learning (ML) artifacts sentiment analysis, market basket modeling, geospatial clustering, and predictive classification as a Design Science Research (DSR) contribution. Through the Knowledge Discovery in Databases (KDD) process, the models were used to illustrate the applicability of the concept of Quality 5.0 in the Saudi Arabian emergent scuba diving industry: human centricity, operational resilience, and holistic sustainability through operationalization by SMEs. Findings indicate the portfolio facilitates emotional mapping of experience, personalization of the curriculum, planning of sites on safety grounds, and ecological mitigation of risk. This research contributes to the applied literature of Quality 5.0 by making the theoretical constructs practical and experienceable through providing a set of guidelines and interpretation, making it a replicable roadmap of introducing AI on data-heavy service-based small and medium-sized enterprises. Quality 5.0 design science research low-code machine learning SMEs operational productivity sentiment analysis predictive classification Figures Figure 1 Figure 2 Figure 3 1. Introduction The galloping prospects of digitization have brought a paradox to the Small and Medium Enterprises (SMEs). The availability of data relating to operational processes, customer interactions, and environmental feedback is higher than ever before, yet most SMEs do not have the capacity to convert raw information into strategic value. Such a disjoint, widely defined as the data-insight gap, presents a serious predicament to quality-centric organizations, especially in service-intensive industries where safety and customer experience are highly interconnected with operational complexity. In parallel, the evolution of Quality 5.0 (Q5) has introduced a paradigm shift in achieving organizational excellence. Extending the values of Quality 4.0, Quality 5.0 focuses on human-centricity, operational resilience, and holistic sustainability. This involves not only data-driven design and work optimization but also sensitive design, future safety interventions, and ecological and social assurance of sustainability. Nevertheless, Q5 is challenging to operationalize, particularly among SMEs that lack sophisticated analytics skills. This paper fills this gap by presenting the design and assessment of a portfolio of four synergistic machine learning (ML) artifacts, developed using a Design Science Research (DSR) methodological approach. The artifacts—sentiment analysis, association rule mining (market basket analysis), geospatial clustering, and predictive classification—are conceptualized as low-code workflows within Orange Data Mining, tailored for non-technical users in the SME environment. Collectively, they offer an interpretable, modular, and scalable quality assurance and decision-making toolkit applicable in real-time. The research is guided by the following overarching question: What is the planning and use of a portfolio of low-code machine learning artifacts that will allow service-based SMEs to execute the Quality 5.0 framework of human-centricity, resilience, and sustainability? This question is further decomposed into three sub-questions: SQ1: How can text mining and association rules models make the service offering of an SME more human-centered? SQ2: How can predictive and unsupervised ML models improve operational resiliency and safety? SQ3: How does synthesized machine learning knowledge aid SMEs in achieving long-term sustainability? The practical implications of this paper will lead to Quality 5.0 implementation, bridging the known theory-practice gap. The advantages extend beyond mere theoretical understanding, providing SME managers with a transferable route to smarter, safer, and more sustainable business performance, legitimately and theoretically supported. 2. Research Methodology The study employed a hybrid methodology based on Design Science Research (DSR) to build and test a portfolio of low-code machine learning (ML) artifacts. DSR served as the general strategic initiative, enabling the development of goal-oriented technological solutions to support SME operations. To facilitate implementation, the Knowledge Discovery in Databases (KDD) process was adopted as a fine-grained, five-fold lifecycle process encompassing data selection, preprocessing, data modeling, and interpretation. The increased rigor of critical reflection methodology and the intersection between DSR and KDD authenticated both methodological rigor and practical applicability in the artifact development cycle. An instrumental case study was conducted within the scuba diving SME sector of Saudi Arabia, aligning with the priorities of Vision 2030 for sustainable tourism and digital transformation. Three types of datasets were utilized: Customer Review Data : A custom web application, developed using Selenium and Streamlit, automated the ethical extraction of customer review data. Transactional Data : Anonymized in-house data from a Saudi dive center, including enrollment trends of over 1,800 customers across 16 different specialty modules. All models were coded on the Orange Data Mining platform (v3.38), which uses a visual programming language emphasizing non-technical users. Orange was chosen for its: Drag-and-drop interface for low-code experimentation. Extensive set of widgets for categorizing, clustering, and text mining. Visual workflows that ensure transparency, reproducibility, and modularity. It is important to note that the research project adhered to ethical standards for conducting research on human subjects and data confidentiality. All proprietary data was anonymized at the source before analysis, preventing any personally identifiable information or sensitive organizational data from being traced back to individual respondents or enterprises. Publicly available datasets were also aggregated and processed without identifiable user data, thereby upholding data protection and privacy standards. 3. Results This section describes the design and assessment of four machine learning (ML) artifacts produced in Orange Data Mining, which support Quality 5.0 by assisting service-based SMEs in translating intricate operational data challenges into viable responses. 3.1 Artifact 1: Sentiment Analysis 3.1.1 Objective To determine levels of customer satisfaction and dissatisfaction by extracting sentiment data from user-generated comments, used to inform interpersonal service delivery and resilience strategies. 3.1.2 Method and Key Findings • Technique: Lexicon-based VADER model applied to preprocessed reviews from TripAdvisor, Instagram, and Google Maps. • Labeling: Reviews were tagged as “Positive” (≥3 stars) or “Negative” (<3 stars). • Accuracy: – Single dive center: 96.39% – Full dataset (top 10 centers): 89% • Key Sentiment Themes: – Positive: “Captain Amr,” “a popular advanced dive site,” “helpful staff,” “safety” – Negative: “waiting time,” “broken regulator,” “bad prices” • Operational Insights: – Human-centricity: Empathy and professionalism were associated with customer praise. – Resilience: Repeated complaints were used to plan proactive service enhancements. – Social sustainability: Community trust grew under the influence of ethical treatment of staff. 3.2 Artifact 2: Market Basket Analysis 3.2.1 Objective To discover tendencies in specialty course enrollment, enabling the development of individualized curriculum plans and sustainable business operational quotes. 3.2.2 Method and Key Findings • Technique: Apriori rule mining on binary-coded data from over 1,800 learners. • Top Rules: – Deep Diver + Night Diver → Dive Master (Confidence: 100%, Lift: 63.5) – Navigation + Nitrox → Night Diving (Confidence: 100%, Lift: 10.4) • Demographic Insights: – Dominant enrollment year: 2024 – Gender: Slight female majority – Nationality: Mostly Saudi, with learners from UK, Spain, UAE – Dive experience clusters: Novice, Technical, and Tourist • Strategic Takeaways: – Curriculum personalization – Inventory alignment (e.g., Nitrox tanks) – Customer lifetime value enhancement – Environmental storytelling via eco-diving bundles 3.3 Artifact 3: Geospatial Clustering 3.3.1 Objective To classify dive sites by entry type and environmental conditions, supporting operational zoning and ecological protection. 3.3.2 Method and Key Findings • Technique: K-Means clustering of standardized site attributes (access type, depth, frequency). • Validation: Silhouette scores and Distance matrix visualization confirmed stable groupings. – Silhouette analysis showed stable scores for every cluster. • Clusters Identified: – Shore Entry: Urban-adjacent training sites – Boat Entry: Remote reefs for advanced divers – Pool Access: Limited-access training zones • Geo Mapping Insights: – Hotspots: Jeddah, Al Lith, Yanbu – Over-dived sites: Abu Tair, Sha Ab Ammar – Current strength distribution: • Pool: No current • Shore: Light current • Boat: Strong/ripping currents • Operational & Sustainability Impacts: – Real-time dive planning and site rotation – Load-balancing to protect fragile reefs – Safety optimization based on cluster-derived insights 3.4 Artifact 4: Predictive Classification 3.4.1 Objective To score and forecast dive site difficulty via supervised ML, assisting in balancing diver capabilities with optimal dive site usage to minimize operational risks. 3.4.2 Method and Key Findings • Technique: AdaBoost classifier trained on site attributes (depth, entry complexity, current). • Classification Levels: – Level 1: Beginner (≤18m, no current) – Level 2: Intermediate (18–30m, medium current) – Level 3: Advanced (>30m, strong current) • Model Accuracy: – High agreement with expert-defined site classes. – Confusion matrix showed minimal misclassification. • Deployment Benefits: – Site planning based on predicted difficulty – Seasonal demand analysis – Multilayered integration with geospatial clusters for itinerary personalization 3.5 Portfolio Synergy and Quality 5.0 Alignment The four artifacts collectively represent a comprehensive toolkit aligned with Quality 5.0 pillars: • Human-centricity: Empathetic insights derived from sentiment analysis and learner profiling. • Resilience: Predictive adjustments in operational plans, equipment provisioning, and staff allocation. • Sustainability: Balanced reef usage, ecological path planning, and ethics-aware curriculum design. Overall, the low-code interface provided by Orange Data Mining facilitated visual documentation of the workflow and interdisciplinary access, ensuring interpretation and rapid learning for SME managers. 4. Discussion This paper demonstrates that a synergistic combination of four low-code machine learning (ML) artifacts—sentiment analysis, market basket modeling, geospatial clustering, and predictive classification—can transform fragmented small and medium enterprise (SME) data streams into executable intelligence, aligning with the concepts of Quality 5.0. Below, we describe the contribution of the empirical findings under each of the three pillars of Q5: human-centricity, operational resilience, and sustainability. 4.1 Operationalizing Human-Centricity Artifacts 1 and 2 are designed to be used together to provide a dual-lens view of the customer: emotional insights through sentiment analysis (Artifact 1) and behavioral trends through association rule mining (Artifact 2). Artifact 1 (Sentiment Analysis) extracted subtle forms of satisfied and dissatisfied complaints from reviews, achieving over 89% correctness in estimating complaint categories. The themes of emotional drivers in personalized service delivery identified high-frequency keywords such as safe,’ ‘friendly,’ and mentions of ‘professional staff. With the help of Artifact 2 (Market Basket Analysis), strategic co-enrollment patterns were identified, such as ‘Deep Diver + Night Diver → Dive Master,’ reflecting the implicit preferences of learners and their learning paths. Using these behavioral routes, dive centers gained data-supported personalization platforms to engage customers, improve security, and maintain their loyalty. Collectively, these artifacts facilitated empathetic curriculum development, predictive service bundling, emotional experience mapping, and embedded human-centric intelligence into both strategic and operational aspects. 4.2 Building Operational Resilience The distinct contributions of Artifacts 3 and 4 enable the development of robust, data-driven planning, logistics optimization, and safety assurance decisions, moving beyond intuition-based approaches. Artifact 3 (Geospatial Clustering) segmented dive sites into logically bounded parts (shore, boat, pool) based on access and environmental characteristics. Validation through silhouette scores and geo-mapping helped identify geographically high-traffic areas and ecologically sensitive zones, facilitating real-time route planning and site rotation. Artifact 4 (Predictive Classification) employed supervised learning to model dive site difficulty levels (Beginner, Intermediate, Advanced) based on depth, current strength, and access complexity. Confusion matrix analysis confirmed minimal misclassification, supporting its use in guide assignment, diver profiling, and risk mitigation. Collectively, these artifacts have developed multilayered operational intelligence that predicts safety demands, balances resources, and normalizes trip planning, among other mechanisms critical for institutionalizing resilience within the high-variability context of the Saudi Arabian diving industry. 4.3 Promoting Sustainable Wholesomeness The four artifacts contribute significantly to promoting sustainable practices. By optimizing dive site usage and protecting fragile ecosystems through geospatial clustering, and by enhancing safety and reducing risks with predictive classification, the framework supports ecological sustainability. Furthermore, the human-centric insights from sentiment analysis and personalized learning paths from market basket analysis foster a deeper connection between divers and the marine environment, encouraging responsible behavior. The overall approach promotes a holistic view of sustainability, encompassing environmental, social, and economic dimensions within the diving industry. Declarations Competing Interests: The authors declare no competing financial or non-financial interests that are directly or indirectly related to the work submitted for publication. Funding: The author did not receive any funding for this work. Author Contribution: Data Availability: The datasets generated during and/or analyzed during the current study are not publicly available due to proprietary restrictions but are available from the corresponding author on reasonable request. Code Availability: The low-code machine learning workflows were developed using Orange Data Mining (v3.38). The specific workflows are available from the corresponding author on reasonable request. Ethics Declarations: The research project was conducted using ethical standards for human subjects and data confidentiality. All proprietary data was masked anonymously at the source before analysis, ensuring no personally identifiable information or sensitive organizational data could be traced back to individuals or enterprises. Publicly available datasets were aggregated and processed without identifiable user data, upholding data protection and privacy standards. Consent for Publication: Not applicable. This manuscript does not contain any identifiable individual data. References Jayashree S et al (2021) Arsovski S (2019) Social oriented quality: From quality 4.0 towards quality 5.0. In Proceedings of the 13th International Quality Conference, Belgrade, Serbia, May ; pp. 397–404 Bansal M, Chana I, Clarke S (2021) A survey on IoT big data. ACM Comput Surv 53:1–59. https://doi.org/10.1145/3419634 Bauer M, van Dinther C, Kiefer D (2020) Machine learning in SME: An empirical study on enablers and success factors. In Proceedings of the 53rd Hawaii International Conference on System Sciences, Maui, HI, USA, 7–10 January https://doi.org/10.24251/HICSS.2020.589 Burggräf P, Steinberg F, Sauer CR, Nettesheim P (2024) Machine learning implementation in small and medium-sized enterprises: Insights and recommendations from a quantitative study. Prod. Eng. in press. https://doi.org/10.1007/s11740-024-01274-2 Campagne JP, Jacot JH, Frein Y, Vitry G A framework to specify a reactive and proactive management system. In Proceedings of the 1995 INRIA/IEEE Symposium on Emerging Technologies and Factory Automation, Paris, France, October 1995; Volume 3, pp. 251–259. https://doi.org/10.1109/ETFA.1995.496725 Chehri A, Chaibi H, Zimmermann A, Saadane R (2023) ChatGPT, how to wire age 5.0 mindsets: Industry, society, healthcare and education? In Human Centred Intelligent Systems: Proceedings of KES HCIS 2023 Conference; Abraham, A., Gandhi, N., Hanne, T., Cattai, T., Rios, R., Eds.; Springer: Singapore, ; pp. 133–142 Chiarini A, Kumar M (2022) What is Quality 4.0? An exploratory sequential mixed methods study of Italian manufacturing companies. Int J Prod Res 60:4890–4910. https://doi.org/10.1080/00207543.2021.1942285 Creswell JW, Plano Clark VL (2018) Designing and conducting mixed methods research, 3rd edn. Sage, Thousand Oaks, CA, USA Fahrenschon G, Kirchhof AG, Simmert DB (2015) Mittelstand – Motor und Zukunft der deutschen Wirtschaft. Springer Fachmedien, Wiesbaden, Germany Fayyad U, Piatetsky-Shapiro G, Smyth P (1996) From data mining to knowledge discovery in databases. AI Mag 17:37–54. https://doi.org/10.1609/aimag.v17i3.1230 Goldkuhl G (2012) Pragmatism versus interpretivism in qualitative information systems research. Eur J Inf Syst 21:135–146. https://doi.org/10.1057/ejis.2011.54 Hauser C, Hogenacker J (2014) Do firms proactively take measures to prevent corruption in their international operations? Eur Manag Rev 11:133–149. https://doi.org/10.1111/emre.12035 Hevner AR, March ST, Park J, Ram S (2004) Design science in information systems research. MIS Q 28:75–105. https://doi.org/10.2307/25148625 Iftikhar N, Nordbjerg FE (2022) Implementing machine learning in small and medium-sized manufacturing enterprises. In: Andersen A-L, Andersen R, Brunoe TD (eds) Towards Sustainable Customization: Bridging Smart Products and Manufacturing Systems. Springer, Cham, Switzerland, pp 448–456 Jayashree S, Reza MNH, Malarvizhi CAN, Mohiuddin M Industry 4.0 implementation and triple bottom line sustainability: An empirical study on small and medium manufacturing firms. Heliyon 2021, 7, e07753. https://doi.org/10.1016/j.heliyon.2021.e07753 Kavitha A (2021) Emerging aspects of artificial intelligence for smart life. Eng Sci Int J 8:83020. https://doi.org/10.30726/esij/v8.i3.2021.83020 Koc T (2007) The impact of ISO 9000 quality management systems on manufacturing. J Mater Process Technol 186:207–213. https://doi.org/10.1016/j.jmatprotec.2006.12.034 Lee I, Shin YJ (2020) Machine learning for enterprises: Applications, algorithm selection, and challenges. Bus Horiz 63:157–170. https://doi.org/10.1016/j.bushor.2019.10.005 Mahesh B (2019) Machine learning algorithms—a review. Int J Sci Res 9:381–386 March ST, Smith GF (1995) Design and natural science research on information technology. Decis Support Syst 15:251–266. https://doi.org/10.1016/0167-9236(94)00041-2 Mehran E, Mehran S (2013) Quality management and performance: An annotated review. Int J Prod Res 51:5625–5643. https://doi.org/10.1080/00207543.2013.793426 Mills M (2020) From reactive to proactive. Qual Prog 53:56 Morgan DL (2014) Pragmatism as a paradigm for social research. Qual Inq 20:1045–1053. https://doi.org/10.1177/1077800413513733 Nahavandi S (2019) Industry 5.0—A human-centric solution. Sustainability 11:4371. https://doi.org/10.3390/su11164371 PADI – Professional Association of Diving Instructors (2025) Available online: https://www.padi.com (accessed on 21 July Pazhayattil AB, Konyu-Fogel G (2023) An empirical study to accelerate machine learning and artificial intelligence adoption in pharmaceutical manufacturing organizations. J Generic Med 19:81–91. https://doi.org/10.1177/17411343221151109 Peirce CS (1931) –1958 Collected papers of Charles Sanders Peirce; Harvard University Press: Cambridge, MA, USA, ; Volumes 1–8 Radziwill N (2018) Let’s get digital: The many ways the fourth industrial revolution is reshaping the way we think about quality. Qual Prog. pp. 24–29 Robertson PS (2020) Man & machine: Adaptive tools for the contemporary performance analyst. J Sports Sci 38:2118–2126. https://doi.org/10.1080/02640414.2020.1774143 Sannö A, Fundin A, Stålberg L (2016) Managing environmentally driven change in manufacturing organisations: Moving from reactive to proactive behavior. Int J Prod Qual Manag 18:347–363. https://doi.org/10.1504/IJPQM.2016.076714 Saunders M, Lewis P, Thornhill A (2019) Research methods for business students, 8th edn. Pearson, Harlow, UK Schölkopf B (2022) Causality for machine learning. In Probabilistic and Causal Inference; Gefner, H., Dechter, R., Halpern, J.Y., Eds.; ACM, ; Vol. 27, pp. 765–804 Stake RE (1995) The art of case study research; Sage Publications: Thousand Oaks, CA, USA KI entwickelt sich in Deutschland nur langsam (2023) Statista. Available online: https://de.statista.com/infografik/22295/umfrage-zum-einsatz-von-kuenstlicher-intelligenz-in-unternehmen/ (accessed on 17 November Talha M (2004) Total quality management (TQM): An overview. Bottom Line 17:15–19. https://doi.org/10.1108/08880450410519656 Thiée (2021) L.W. A systematic literature review of machine learning canvases. In INFORMATIK 2021, Lecture Notes in Informatics Timmermans S, Tavory I (2012) Theory construction in qualitative research: From grounded theory to abductive analysis. Sociol Theory 30:167–186. https://doi.org/10.1177/0735275112457914 Van Aken JE (2004) Management research based on the paradigm of the design sciences: The quest for field-tested and grounded technological rules. J Manag Stud 41:219–246. https://doi.org/10.1111/j.1467-6486.2004.00430.x an de Ven AH (2007) Engaged scholarship: A guide for organizational and social research. Oxford University Press, New York, NY, USA Yin RK (2018) Case study research and applications: Design and methods, 6th edn. Sage, Thousand Oaks, CA, USA Additional Declarations No competing interests reported. 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-7839321","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":529338913,"identity":"00ca36c1-fbed-4102-a874-3faee874053b","order_by":0,"name":"Islam Gad","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAvElEQVRIiWNgGAWjYBACNghpAyQYGw+QoiUNpKWBOC1QjYfBFHFa+PhXJ7/4UXbebm37YaAtNTbRhM2XeLvNsufc7eRtZxKBWo6l5TYQ1nJ2mwFv2+1kswNALYwNh4nTYvi37Vyy2fmHxGrh7938mLftgJ3ZDeJt4d3GLHMuOcHsBtCWBGL8It9/dvPHN2V29mbn0x8++FBjQ1gLg0QCmwSQSgSrTCCoHAT4DzB/AFL2RCkeBaNgFIyCkQkAkORJLjaNCWEAAAAASUVORK5CYII=","orcid":"","institution":"Arab Academy for Science, Technology \u0026 Maritime Transport (AASTMT)","correspondingAuthor":true,"prefix":"","firstName":"Islam","middleName":"","lastName":"Gad","suffix":""},{"id":529338914,"identity":"f5cd80f3-c19a-4b8c-b3d2-e520b2c5361c","order_by":1,"name":"Mohamed Mahmoud","email":"","orcid":"","institution":"Arab Academy for Science, Technology \u0026 Maritime Transport (AASTMT)","correspondingAuthor":false,"prefix":"","firstName":"Mohamed","middleName":"","lastName":"Mahmoud","suffix":""},{"id":529338917,"identity":"8dde19e9-f1d0-49d1-b7a5-9f5f05e1dbcb","order_by":2,"name":"Iman Nassef","email":"","orcid":"","institution":"Arab Academy for Science, Technology \u0026 Maritime Transport (AASTMT)","correspondingAuthor":false,"prefix":"","firstName":"Iman","middleName":"","lastName":"Nassef","suffix":""}],"badges":[],"createdAt":"2025-10-12 08:23:20","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7839321/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7839321/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":93553352,"identity":"e0e2b177-f626-4e79-a598-214a9a110622","added_by":"auto","created_at":"2025-10-15 05:56:57","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":478989,"visible":true,"origin":"","legend":"","description":"","filename":"manuscriptspringer.docx","url":"https://assets-eu.researchsquare.com/files/rs-7839321/v1/b1481c48dd193012af06f2a9.docx"},{"id":93553418,"identity":"cd9d8cdc-060b-4b0f-82b9-21de801a7f50","added_by":"auto","created_at":"2025-10-15 06:04:57","extension":"json","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":5026,"visible":true,"origin":"","legend":"","description":"","filename":"25a38f14d40b419abdc6db622a8e05fe.json","url":"https://assets-eu.researchsquare.com/files/rs-7839321/v1/9134f02c9253f519d40a347f.json"},{"id":93554597,"identity":"1306d914-ce26-4dbd-a599-9dacbf526992","added_by":"auto","created_at":"2025-10-15 06:20:57","extension":"xml","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":78127,"visible":true,"origin":"","legend":"","description":"","filename":"25a38f14d40b419abdc6db622a8e05fe1enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-7839321/v1/9effb08958c0070c2121da5f.xml"},{"id":93553351,"identity":"7e53f7f9-95db-4de7-a64d-69151dc859ac","added_by":"auto","created_at":"2025-10-15 05:56:57","extension":"jpeg","order_by":17,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":307562,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage1.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7839321/v1/dec4c035f1f98d105c9acba1.jpeg"},{"id":93553348,"identity":"cd265604-be1c-47a2-a373-7957960e2493","added_by":"auto","created_at":"2025-10-15 05:56:57","extension":"jpeg","order_by":18,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":42753,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage2.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7839321/v1/0c3de6d61a5d19fef36b92ba.jpeg"},{"id":93553349,"identity":"a196eee0-c8a2-4ed1-b593-35daafb9f29b","added_by":"auto","created_at":"2025-10-15 05:56:57","extension":"jpeg","order_by":19,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":94595,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage3.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7839321/v1/36235fd9c9f866d1e67be7aa.jpeg"},{"id":93553422,"identity":"050e7574-7718-4d9d-b59b-f52a031e7123","added_by":"auto","created_at":"2025-10-15 06:04:58","extension":"png","order_by":20,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":159421,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-7839321/v1/718042fa28744fb12c98b755.png"},{"id":93553353,"identity":"184be440-3c4f-47fa-b83d-1801e786f679","added_by":"auto","created_at":"2025-10-15 05:56:58","extension":"png","order_by":21,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":8315,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-7839321/v1/7f5344f1f3ab62f534adf484.png"},{"id":93553350,"identity":"098c4039-c31c-4071-98e0-9b7f9a378de4","added_by":"auto","created_at":"2025-10-15 05:56:57","extension":"png","order_by":22,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":48955,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-7839321/v1/d6293ef57ec25d8a181425a4.png"},{"id":93553356,"identity":"d9dec7a3-3a5b-4a4b-b1ed-eec4d92ed385","added_by":"auto","created_at":"2025-10-15 05:56:58","extension":"xml","order_by":23,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":73871,"visible":true,"origin":"","legend":"","description":"","filename":"25a38f14d40b419abdc6db622a8e05fe1structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-7839321/v1/cfe47a078d19605e9f44fece.xml"},{"id":93553354,"identity":"cd942a6f-d336-4e9d-b4a6-e5d7706a3c6a","added_by":"auto","created_at":"2025-10-15 05:56:58","extension":"html","order_by":24,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":94398,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-7839321/v1/f044e3638785867827ad7b78.html"},{"id":93553340,"identity":"b68aaa74-80e9-490a-b6dc-1ac9f46acf84","added_by":"auto","created_at":"2025-10-15 05:56:57","extension":"jpg","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":131614,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eWord cloud showing positive sentiment themes from top-rated dive center reviews.\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"1.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7839321/v1/fd90b25dd757404100015621.jpg"},{"id":93553417,"identity":"9ab0dc1e-ca0c-4f3d-b6fd-f0d1cbfb8293","added_by":"auto","created_at":"2025-10-15 06:04:57","extension":"jpg","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":70261,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eSilhouette plot validating K-Means cluster strength across dive site segments.\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"2.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7839321/v1/008c41a29e175b12299581ac.jpg"},{"id":93553419,"identity":"0de4777c-add2-491f-aa94-4266a34d7e59","added_by":"auto","created_at":"2025-10-15 06:04:57","extension":"jpg","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":41989,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eConfusion matrix from AdaBoost model evaluating dive site risk classification performance.\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"3.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7839321/v1/ff2120a3491433680b56a034.jpg"},{"id":96254461,"identity":"30a2ec47-2569-4ead-9a47-29929ce2c624","added_by":"auto","created_at":"2025-11-19 07:46:42","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1143792,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7839321/v1/3fa82218-2002-4263-bdac-e844f9f79f66.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"The Impact of Machine Learning on Business Productivity: A Comprehensive Study within the Quality 5.0 Framework","fulltext":[{"header":"1. Introduction","content":"\u003cp\u003eThe galloping prospects of digitization have brought a paradox to the Small and Medium Enterprises (SMEs). The availability of data relating to operational processes, customer interactions, and environmental feedback is higher than ever before, yet most SMEs do not have the capacity to convert raw information into strategic value. Such a disjoint, widely defined as the data-insight gap, presents a serious predicament to quality-centric organizations, especially in service-intensive industries where safety and customer experience are highly interconnected with operational complexity.\u003c/p\u003e\u003cp\u003eIn parallel, the evolution of Quality 5.0 (Q5) has introduced a paradigm shift in achieving organizational excellence. Extending the values of Quality 4.0, Quality 5.0 focuses on human-centricity, operational resilience, and holistic sustainability. This involves not only data-driven design and work optimization but also sensitive design, future safety interventions, and ecological and social assurance of sustainability. Nevertheless, Q5 is challenging to operationalize, particularly among SMEs that lack sophisticated analytics skills.\u003c/p\u003e\u003cp\u003eThis paper fills this gap by presenting the design and assessment of a portfolio of four synergistic machine learning (ML) artifacts, developed using a Design Science Research (DSR) methodological approach. The artifacts\u0026mdash;sentiment analysis, association rule mining (market basket analysis), geospatial clustering, and predictive classification\u0026mdash;are conceptualized as low-code workflows within Orange Data Mining, tailored for non-technical users in the SME environment. Collectively, they offer an interpretable, modular, and scalable quality assurance and decision-making toolkit applicable in real-time.\u003c/p\u003e\u003cp\u003eThe research is guided by the following overarching question:\u003c/p\u003e\u003cp\u003eWhat is the planning and use of a portfolio of low-code machine learning artifacts that will allow service-based SMEs to execute the Quality 5.0 framework of human-centricity, resilience, and sustainability?\u003c/p\u003e\u003cp\u003eThis question is further decomposed into three sub-questions:\u003c/p\u003e\u003cp\u003e\u003cul\u003e\u003cli\u003e\u003cp\u003eSQ1: How can text mining and association rules models make the service offering of an SME more human-centered?\u003c/p\u003e\u003c/li\u003e\u003cli\u003e\u003cp\u003eSQ2: How can predictive and unsupervised ML models improve operational resiliency and safety?\u003c/p\u003e\u003c/li\u003e\u003cli\u003e\u003cp\u003eSQ3: How does synthesized machine learning knowledge aid SMEs in achieving long-term sustainability?\u003c/p\u003e\u003c/li\u003e\u003c/ul\u003e\u003c/p\u003e\u003cp\u003eThe practical implications of this paper will lead to Quality 5.0 implementation, bridging the known theory-practice gap. The advantages extend beyond mere theoretical understanding, providing SME managers with a transferable route to smarter, safer, and more sustainable business performance, legitimately and theoretically supported.\u003c/p\u003e\u003cp\u003e\u003c/p\u003e"},{"header":"2. Research Methodology","content":"\u003cp\u003eThe study employed a hybrid methodology based on Design Science Research (DSR) to build and test a portfolio of low-code machine learning (ML) artifacts. DSR served as the general strategic initiative, enabling the development of goal-oriented technological solutions to support SME operations. To facilitate implementation, the Knowledge Discovery in Databases (KDD) process was adopted as a fine-grained, five-fold lifecycle process encompassing data selection, preprocessing, data modeling, and interpretation. The increased rigor of critical reflection methodology and the intersection between DSR and KDD authenticated both methodological rigor and practical applicability in the artifact development cycle.\u003c/p\u003e\u003cp\u003eAn instrumental case study was conducted within the scuba diving SME sector of Saudi Arabia, aligning with the priorities of Vision 2030 for sustainable tourism and digital transformation.\u003c/p\u003e\u003cp\u003eThree types of datasets were utilized:\u003c/p\u003e\u003cp\u003e\u003cul\u003e\u003cli\u003e\u003cp\u003e\u003cb\u003eCustomer Review Data\u003c/b\u003e: A custom web application, developed using Selenium and Streamlit, automated the ethical extraction of customer review data.\u003c/p\u003e\u003c/li\u003e\u003cli\u003e\u003cp\u003e\u003cb\u003eTransactional Data\u003c/b\u003e: Anonymized in-house data from a Saudi dive center, including enrollment trends of over 1,800 customers across 16 different specialty modules.\u003c/p\u003e\u003c/li\u003e\u003c/ul\u003e\u003c/p\u003e\u003cp\u003eAll models were coded on the Orange Data Mining platform (v3.38), which uses a visual programming language emphasizing non-technical users. Orange was chosen for its:\u003c/p\u003e\u003cp\u003e\u003cul\u003e\u003cli\u003e\u003cp\u003eDrag-and-drop interface for low-code experimentation.\u003c/p\u003e\u003c/li\u003e\u003cli\u003e\u003cp\u003eExtensive set of widgets for categorizing, clustering, and text mining.\u003c/p\u003e\u003c/li\u003e\u003cli\u003e\u003cp\u003eVisual workflows that ensure transparency, reproducibility, and modularity.\u003c/p\u003e\u003c/li\u003e\u003c/ul\u003e\u003c/p\u003e\u003cp\u003eIt is important to note that the research project adhered to ethical standards for conducting research on human subjects and data confidentiality. All proprietary data was anonymized at the source before analysis, preventing any personally identifiable information or sensitive organizational data from being traced back to individual respondents or enterprises. Publicly available datasets were also aggregated and processed without identifiable user data, thereby upholding data protection and privacy standards.\u003c/p\u003e\u003cp\u003e\u003c/p\u003e"},{"header":"3. Results","content":"\u003cp\u003eThis section describes the design and assessment of four machine learning (ML) artifacts produced in Orange Data Mining, which support Quality 5.0 by assisting service-based SMEs in translating intricate operational data challenges into viable responses.\u003c/p\u003e\n\u003ch3\u003e3.1 Artifact 1: Sentiment Analysis\u003c/h3\u003e\n\u003ch4\u003e3.1.1 Objective\u003c/h4\u003e\n\u003cp\u003eTo determine levels of customer satisfaction and dissatisfaction by extracting sentiment data from user-generated comments, used to inform interpersonal service delivery and resilience strategies.\u003c/p\u003e\n\u003ch4\u003e3.1.2 Method and Key Findings\u003c/h4\u003e\n\u003cp\u003e\u0026bull;\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;\u003cstrong\u003eTechnique:\u003c/strong\u003e Lexicon-based VADER model applied to preprocessed reviews from TripAdvisor, Instagram, and Google Maps.\u003c/p\u003e\n\u003cp\u003e\u0026bull;\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;\u003cstrong\u003eLabeling:\u003c/strong\u003e Reviews were tagged as \u0026ldquo;Positive\u0026rdquo; (\u0026ge;3 stars) or \u0026ldquo;Negative\u0026rdquo; (\u0026lt;3 stars).\u003c/p\u003e\n\u003cp\u003e\u0026bull;\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;\u003cstrong\u003eAccuracy:\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e\u0026ndash;\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;Single dive center: 96.39%\u003c/p\u003e\n\u003cp\u003e\u0026ndash;\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;Full dataset (top 10 centers): 89%\u003c/p\u003e\n\u003cp\u003e\u0026bull;\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;\u003cstrong\u003eKey Sentiment Themes:\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e\u0026ndash;\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;Positive: \u0026ldquo;Captain Amr,\u0026rdquo; \u0026ldquo;a popular advanced dive site,\u0026rdquo; \u0026ldquo;helpful staff,\u0026rdquo; \u0026ldquo;safety\u0026rdquo;\u003c/p\u003e\n\u003cp\u003e\u0026ndash;\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;Negative: \u0026ldquo;waiting time,\u0026rdquo; \u0026ldquo;broken regulator,\u0026rdquo; \u0026ldquo;bad prices\u0026rdquo;\u003c/p\u003e\n\u003cp\u003e\u0026bull;\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;\u003cstrong\u003eOperational Insights:\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e\u0026ndash;\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;\u003cstrong\u003eHuman-centricity:\u003c/strong\u003e Empathy and professionalism were associated with customer praise.\u003c/p\u003e\n\u003cp\u003e\u0026ndash;\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;\u003cstrong\u003eResilience:\u003c/strong\u003e Repeated complaints were used to plan proactive service enhancements.\u003c/p\u003e\n\u003cp\u003e\u0026ndash; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u003cstrong\u003eSocial sustainability:\u003c/strong\u003e Community trust grew under the influence of ethical treatment of staff.\u003c/p\u003e\n\u003ch3\u003e3.2 Artifact 2: Market Basket Analysis\u003c/h3\u003e\n\u003ch4\u003e3.2.1 Objective\u003c/h4\u003e\n\u003cp\u003eTo discover tendencies in specialty course enrollment, enabling the development of individualized curriculum plans and sustainable business operational quotes.\u003c/p\u003e\n\u003ch4\u003e3.2.2 Method and Key Findings\u003c/h4\u003e\n\u003cp\u003e\u0026bull;\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;\u003cstrong\u003eTechnique:\u003c/strong\u003e Apriori rule mining on binary-coded data from over 1,800 learners.\u003c/p\u003e\n\u003cp\u003e\u0026bull;\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;\u003cstrong\u003eTop Rules:\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e\u0026ndash;\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;Deep Diver + Night Diver \u0026rarr; Dive Master (Confidence: 100%, Lift: 63.5)\u003c/p\u003e\n\u003cp\u003e\u0026ndash;\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;Navigation + Nitrox \u0026rarr; Night Diving (Confidence: 100%, Lift: 10.4)\u003c/p\u003e\n\u003cp\u003e\u0026bull;\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;\u003cstrong\u003eDemographic Insights:\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e\u0026ndash;\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;Dominant enrollment year: 2024\u003c/p\u003e\n\u003cp\u003e\u0026ndash;\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;Gender: Slight female majority\u003c/p\u003e\n\u003cp\u003e\u0026ndash;\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;Nationality: Mostly Saudi, with learners from UK, Spain, UAE\u003c/p\u003e\n\u003cp\u003e\u0026ndash;\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;Dive experience clusters: Novice, Technical, and Tourist\u003c/p\u003e\n\u003cp\u003e\u0026bull;\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;\u003cstrong\u003eStrategic Takeaways:\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e\u0026ndash;\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;Curriculum personalization\u003c/p\u003e\n\u003cp\u003e\u0026ndash;\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;Inventory alignment (e.g., Nitrox tanks)\u003c/p\u003e\n\u003cp\u003e\u0026ndash;\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;Customer lifetime value enhancement\u003c/p\u003e\n\u003cp\u003e\u0026ndash;\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;Environmental storytelling via eco-diving bundles\u003c/p\u003e\n\u003ch3\u003e3.3 Artifact 3: Geospatial Clustering\u003c/h3\u003e\n\u003ch4\u003e3.3.1 Objective\u003c/h4\u003e\n\u003cp\u003eTo classify dive sites by entry type and environmental conditions, supporting operational zoning and ecological protection.\u003c/p\u003e\n\u003ch4\u003e3.3.2 Method and Key Findings\u003c/h4\u003e\n\u003cp\u003e\u0026bull;\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;\u003cstrong\u003eTechnique:\u003c/strong\u003e K-Means clustering of standardized site attributes (access type, depth, frequency).\u003c/p\u003e\n\u003cp\u003e\u0026bull;\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;\u003cstrong\u003eValidation:\u003c/strong\u003e Silhouette scores and Distance matrix visualization confirmed stable groupings.\u003c/p\u003e\n\u003cp\u003e\u0026ndash; \u0026nbsp; \u0026nbsp; \u0026nbsp; Silhouette analysis showed stable scores for every cluster.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e\u0026bull;\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;Clusters Identified:\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e\u0026ndash;\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;Shore Entry: Urban-adjacent training sites\u003c/p\u003e\n\u003cp\u003e\u0026ndash;\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;Boat Entry: Remote reefs for advanced divers\u003c/p\u003e\n\u003cp\u003e\u0026ndash;\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;Pool Access: Limited-access training zones\u003c/p\u003e\n\u003cp\u003e\u0026bull;\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;\u003cstrong\u003eGeo Mapping Insights:\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e\u0026ndash;\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;Hotspots: Jeddah, Al Lith, Yanbu\u003c/p\u003e\n\u003cp\u003e\u0026ndash;\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;Over-dived sites: Abu Tair, Sha Ab Ammar\u003c/p\u003e\n\u003cp\u003e\u0026ndash;\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;Current strength distribution:\u003c/p\u003e\n\u003cp\u003e\u0026bull;\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;Pool: No current\u003c/p\u003e\n\u003cp\u003e\u0026bull;\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;Shore: Light current\u003c/p\u003e\n\u003cp\u003e\u0026bull;\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;Boat: Strong/ripping currents\u003c/p\u003e\n\u003cp\u003e\u0026bull;\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;\u003cstrong\u003eOperational \u0026amp; Sustainability Impacts:\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e\u0026ndash;\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;Real-time dive planning and site rotation\u003c/p\u003e\n\u003cp\u003e\u0026ndash;\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;Load-balancing to protect fragile reefs\u003c/p\u003e\n\u003cp\u003e\u0026ndash; \u0026nbsp; \u0026nbsp; \u0026nbsp; Safety optimization based on cluster-derived insights\u003c/p\u003e\n\u003ch3\u003e3.4 Artifact 4: Predictive Classification\u003c/h3\u003e\n\u003ch4\u003e3.4.1 Objective\u003c/h4\u003e\n\u003cp\u003eTo score and forecast dive site difficulty via supervised ML, assisting in balancing diver capabilities with optimal dive site usage to minimize operational risks.\u003c/p\u003e\n\u003ch4\u003e3.4.2 Method and Key Findings\u003c/h4\u003e\n\u003cp\u003e\u0026bull;\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;\u003cstrong\u003eTechnique:\u003c/strong\u003e AdaBoost classifier trained on site attributes (depth, entry complexity, current).\u003c/p\u003e\n\u003cp\u003e\u0026bull;\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;\u003cstrong\u003eClassification Levels:\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e\u0026ndash;\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;Level 1: Beginner (\u0026le;18m, no current)\u003c/p\u003e\n\u003cp\u003e\u0026ndash;\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;Level 2: Intermediate (18\u0026ndash;30m, medium current)\u003c/p\u003e\n\u003cp\u003e\u0026ndash;\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;Level 3: Advanced (\u0026gt;30m, strong current)\u003c/p\u003e\n\u003cp\u003e\u0026bull;\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;\u003cstrong\u003eModel Accuracy:\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e\u0026ndash;\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;High agreement with expert-defined site classes.\u003c/p\u003e\n\u003cp\u003e\u0026ndash;\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;Confusion matrix showed minimal misclassification.\u003c/p\u003e\n\u003cp\u003e\u0026bull;\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;\u003cstrong\u003eDeployment Benefits:\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e\u0026ndash;\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;Site planning based on predicted difficulty\u003c/p\u003e\n\u003cp\u003e\u0026ndash;\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;Seasonal demand analysis\u003c/p\u003e\n\u003cp\u003e\u0026ndash; \u0026nbsp; \u0026nbsp; \u0026nbsp; Multilayered integration with geospatial clusters for itinerary personalization\u003c/p\u003e\n\u003ch3\u003e3.5 Portfolio Synergy and Quality 5.0 Alignment\u003c/h3\u003e\n\u003cp\u003eThe four artifacts collectively represent a comprehensive toolkit aligned with Quality 5.0 pillars:\u003c/p\u003e\n\u003cp\u003e\u0026bull;\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;\u003cstrong\u003eHuman-centricity:\u003c/strong\u003e Empathetic insights derived from sentiment analysis and learner profiling.\u003c/p\u003e\n\u003cp\u003e\u0026bull;\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;\u003cstrong\u003eResilience:\u003c/strong\u003e Predictive adjustments in operational plans, equipment provisioning, and staff allocation.\u003c/p\u003e\n\u003cp\u003e\u0026bull;\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;\u003cstrong\u003eSustainability:\u003c/strong\u003e Balanced reef usage, ecological path planning, and ethics-aware curriculum design.\u003c/p\u003e\n\u003cp\u003eOverall, the low-code interface provided by Orange Data Mining facilitated visual documentation of the workflow and interdisciplinary access, ensuring interpretation and rapid learning for SME managers.\u003c/p\u003e"},{"header":"4. Discussion","content":"\u003cp\u003eThis paper demonstrates that a synergistic combination of four low-code machine learning (ML) artifacts\u0026mdash;sentiment analysis, market basket modeling, geospatial clustering, and predictive classification\u0026mdash;can transform fragmented small and medium enterprise (SME) data streams into executable intelligence, aligning with the concepts of Quality 5.0. Below, we describe the contribution of the empirical findings under each of the three pillars of Q5: human-centricity, operational resilience, and sustainability.\u003c/p\u003e\u003cdiv id=\"Sec18\" class=\"Section2\"\u003e\u003ch2\u003e4.1 Operationalizing Human-Centricity\u003c/h2\u003e\u003cp\u003eArtifacts 1 and 2 are designed to be used together to provide a dual-lens view of the customer: emotional insights through sentiment analysis (Artifact 1) and behavioral trends through association rule mining (Artifact 2).\u003c/p\u003e\u003cp\u003eArtifact 1 (Sentiment Analysis) extracted subtle forms of satisfied and dissatisfied complaints from reviews, achieving over 89% correctness in estimating complaint categories. The themes of emotional drivers in personalized service delivery identified high-frequency keywords such as\u003cdiv class=\"BlockQuote\"\u003e\u003cp\u003esafe,\u0026rsquo; \u0026lsquo;friendly,\u0026rsquo; and mentions of \u0026lsquo;professional staff.\u003c/p\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003eWith the help of Artifact 2 (Market Basket Analysis), strategic co-enrollment patterns were identified, such as \u0026lsquo;Deep Diver\u0026thinsp;+\u0026thinsp;Night Diver \u0026rarr; Dive Master,\u0026rsquo; reflecting the implicit preferences of learners and their learning paths. Using these behavioral routes, dive centers gained data-supported personalization platforms to engage customers, improve security, and maintain their loyalty.\u003c/p\u003e\u003cp\u003eCollectively, these artifacts facilitated empathetic curriculum development, predictive service bundling, emotional experience mapping, and embedded human-centric intelligence into both strategic and operational aspects.\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec19\" class=\"Section2\"\u003e\u003ch2\u003e4.2 Building Operational Resilience\u003c/h2\u003e\u003cp\u003eThe distinct contributions of Artifacts 3 and 4 enable the development of robust, data-driven planning, logistics optimization, and safety assurance decisions, moving beyond intuition-based approaches.\u003c/p\u003e\u003cp\u003eArtifact 3 (Geospatial Clustering) segmented dive sites into logically bounded parts (shore, boat, pool) based on access and environmental characteristics. Validation through silhouette scores and geo-mapping helped identify geographically high-traffic areas and ecologically sensitive zones, facilitating real-time route planning and site rotation.\u003c/p\u003e\u003cp\u003eArtifact 4 (Predictive Classification) employed supervised learning to model dive site difficulty levels (Beginner, Intermediate, Advanced) based on depth, current strength, and access complexity. Confusion matrix analysis confirmed minimal misclassification, supporting its use in guide assignment, diver profiling, and risk mitigation.\u003c/p\u003e\u003cp\u003eCollectively, these artifacts have developed multilayered operational intelligence that predicts safety demands, balances resources, and normalizes trip planning, among other mechanisms critical for institutionalizing resilience within the high-variability context of the Saudi Arabian diving industry.\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec20\" class=\"Section2\"\u003e\u003ch2\u003e4.3 Promoting Sustainable Wholesomeness\u003c/h2\u003e\u003cp\u003eThe four artifacts contribute significantly to promoting sustainable practices. By optimizing dive site usage and protecting fragile ecosystems through geospatial clustering, and by enhancing safety and reducing risks with predictive classification, the framework supports ecological sustainability. Furthermore, the human-centric insights from sentiment analysis and personalized learning paths from market basket analysis foster a deeper connection between divers and the marine environment, encouraging responsible behavior. The overall approach promotes a holistic view of sustainability, encompassing environmental, social, and economic dimensions within the diving industry.\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003c/div\u003e"},{"header":"Declarations","content":"\u003cp\u003e\u003cstrong\u003eCompeting Interests:\u003c/strong\u003e The authors declare no competing financial or non-financial interests that are directly or indirectly related to the work submitted for publication.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eFunding:\u0026nbsp;\u003c/strong\u003eThe author did not receive any funding for this work.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAuthor Contribution:\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eData Availability:\u003c/strong\u003e The datasets generated during and/or analyzed during the current study are not publicly available due to proprietary restrictions but are available from the corresponding author on reasonable request.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eCode Availability:\u003c/strong\u003e The low-code machine learning workflows were developed using Orange Data Mining (v3.38). The specific workflows are available from the corresponding author on reasonable request.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eEthics Declarations:\u003c/strong\u003e The research project was conducted using ethical standards for human subjects and data confidentiality. All proprietary data was masked anonymously at the source before analysis, ensuring no personally identifiable information or sensitive organizational data could be traced back to individuals or enterprises. Publicly available datasets were aggregated and processed without identifiable user data, upholding data protection and privacy standards.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConsent for Publication:\u003c/strong\u003e Not applicable. This manuscript does not contain any identifiable individual data.\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\u003cli\u003e\u003cspan\u003eJayashree S et al (2021)\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eArsovski S (2019) Social oriented quality: From quality 4.0 towards quality 5.0. In Proceedings of the 13th International Quality Conference, Belgrade, Serbia, May ; pp. 397\u0026ndash;404\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eBansal M, Chana I, Clarke S (2021) A survey on IoT big data. ACM Comput Surv 53:1\u0026ndash;59. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1145/3419634\u003c/span\u003e\u003cspan address=\"10.1145/3419634\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eBauer M, van Dinther C, Kiefer D (2020) Machine learning in SME: An empirical study on enablers and success factors. In Proceedings of the 53rd Hawaii International Conference on System Sciences, Maui, HI, USA, 7\u0026ndash;10 January \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.24251/HICSS.2020.589\u003c/span\u003e\u003cspan address=\"10.24251/HICSS.2020.589\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eBurggr\u0026auml;f P, Steinberg F, Sauer CR, Nettesheim P (2024) Machine learning implementation in small and medium-sized enterprises: Insights and recommendations from a quantitative study. Prod. Eng. in press. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1007/s11740-024-01274-2\u003c/span\u003e\u003cspan address=\"10.1007/s11740-024-01274-2\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eCampagne JP, Jacot JH, Frein Y, Vitry G A framework to specify a reactive and proactive management system. In Proceedings of the 1995 INRIA/IEEE Symposium on Emerging Technologies and Factory Automation, Paris, France, October 1995; Volume 3, pp. 251\u0026ndash;259. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1109/ETFA.1995.496725\u003c/span\u003e\u003cspan address=\"10.1109/ETFA.1995.496725\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eChehri A, Chaibi H, Zimmermann A, Saadane R (2023) ChatGPT, how to wire age 5.0 mindsets: Industry, society, healthcare and education? In Human Centred Intelligent Systems: Proceedings of KES HCIS 2023 Conference; Abraham, A., Gandhi, N., Hanne, T., Cattai, T., Rios, R., Eds.; Springer: Singapore, ; pp. 133\u0026ndash;142\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eChiarini A, Kumar M (2022) What is Quality 4.0? An exploratory sequential mixed methods study of Italian manufacturing companies. Int J Prod Res 60:4890\u0026ndash;4910. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1080/00207543.2021.1942285\u003c/span\u003e\u003cspan address=\"10.1080/00207543.2021.1942285\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eCreswell JW, Plano Clark VL (2018) Designing and conducting mixed methods research, 3rd edn. Sage, Thousand Oaks, CA, USA\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eFahrenschon G, Kirchhof AG, Simmert DB (2015) Mittelstand \u0026ndash; Motor und Zukunft der deutschen Wirtschaft. Springer Fachmedien, Wiesbaden, Germany\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eFayyad U, Piatetsky-Shapiro G, Smyth P (1996) From data mining to knowledge discovery in databases. AI Mag 17:37\u0026ndash;54. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1609/aimag.v17i3.1230\u003c/span\u003e\u003cspan address=\"10.1609/aimag.v17i3.1230\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eGoldkuhl G (2012) Pragmatism versus interpretivism in qualitative information systems research. Eur J Inf Syst 21:135\u0026ndash;146. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1057/ejis.2011.54\u003c/span\u003e\u003cspan address=\"10.1057/ejis.2011.54\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eHauser C, Hogenacker J (2014) Do firms proactively take measures to prevent corruption in their international operations? Eur Manag Rev 11:133\u0026ndash;149. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1111/emre.12035\u003c/span\u003e\u003cspan address=\"10.1111/emre.12035\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eHevner AR, March ST, Park J, Ram S (2004) Design science in information systems research. MIS Q 28:75\u0026ndash;105. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.2307/25148625\u003c/span\u003e\u003cspan address=\"10.2307/25148625\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eIftikhar N, Nordbjerg FE (2022) Implementing machine learning in small and medium-sized manufacturing enterprises. In: Andersen A-L, Andersen R, Brunoe TD (eds) Towards Sustainable Customization: Bridging Smart Products and Manufacturing Systems. Springer, Cham, Switzerland, pp 448\u0026ndash;456\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eJayashree S, Reza MNH, Malarvizhi CAN, Mohiuddin M Industry 4.0 implementation and triple bottom line sustainability: An empirical study on small and medium manufacturing firms. Heliyon 2021, 7, e07753. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/j.heliyon.2021.e07753\u003c/span\u003e\u003cspan address=\"10.1016/j.heliyon.2021.e07753\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eKavitha A (2021) Emerging aspects of artificial intelligence for smart life. Eng Sci Int J 8:83020. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.30726/esij/v8.i3.2021.83020\u003c/span\u003e\u003cspan address=\"10.30726/esij/v8.i3.2021.83020\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eKoc T (2007) The impact of ISO 9000 quality management systems on manufacturing. J Mater Process Technol 186:207\u0026ndash;213. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/j.jmatprotec.2006.12.034\u003c/span\u003e\u003cspan address=\"10.1016/j.jmatprotec.2006.12.034\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eLee I, Shin YJ (2020) Machine learning for enterprises: Applications, algorithm selection, and challenges. Bus Horiz 63:157\u0026ndash;170. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/j.bushor.2019.10.005\u003c/span\u003e\u003cspan address=\"10.1016/j.bushor.2019.10.005\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eMahesh B (2019) Machine learning algorithms\u0026mdash;a review. Int J Sci Res 9:381\u0026ndash;386\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eMarch ST, Smith GF (1995) Design and natural science research on information technology. Decis Support Syst 15:251\u0026ndash;266. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/0167-9236(94)00041-2\u003c/span\u003e\u003cspan address=\"10.1016/0167-9236(94)00041-2\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eMehran E, Mehran S (2013) Quality management and performance: An annotated review. Int J Prod Res 51:5625\u0026ndash;5643. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1080/00207543.2013.793426\u003c/span\u003e\u003cspan address=\"10.1080/00207543.2013.793426\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eMills M (2020) From reactive to proactive. Qual Prog 53:56\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eMorgan DL (2014) Pragmatism as a paradigm for social research. Qual Inq 20:1045\u0026ndash;1053. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1177/1077800413513733\u003c/span\u003e\u003cspan address=\"10.1177/1077800413513733\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eNahavandi S (2019) Industry 5.0\u0026mdash;A human-centric solution. Sustainability 11:4371. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.3390/su11164371\u003c/span\u003e\u003cspan address=\"10.3390/su11164371\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003ePADI \u0026ndash; Professional Association of Diving Instructors (2025) Available online: \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://www.padi.com\u003c/span\u003e\u003cspan address=\"https://www.padi.com\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (accessed on 21 July\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003ePazhayattil AB, Konyu-Fogel G (2023) An empirical study to accelerate machine learning and artificial intelligence adoption in pharmaceutical manufacturing organizations. J Generic Med 19:81\u0026ndash;91. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1177/17411343221151109\u003c/span\u003e\u003cspan address=\"10.1177/17411343221151109\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003ePeirce CS (1931) \u0026ndash;1958 Collected papers of Charles Sanders Peirce; Harvard University Press: Cambridge, MA, USA, ; Volumes 1\u0026ndash;8\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eRadziwill N (2018) Let\u0026rsquo;s get digital: The many ways the fourth industrial revolution is reshaping the way we think about quality. Qual Prog. pp. 24\u0026ndash;29\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eRobertson PS (2020) Man \u0026amp; machine: Adaptive tools for the contemporary performance analyst. J Sports Sci 38:2118\u0026ndash;2126. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1080/02640414.2020.1774143\u003c/span\u003e\u003cspan address=\"10.1080/02640414.2020.1774143\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eSann\u0026ouml; A, Fundin A, St\u0026aring;lberg L (2016) Managing environmentally driven change in manufacturing organisations: Moving from reactive to proactive behavior. Int J Prod Qual Manag 18:347\u0026ndash;363. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1504/IJPQM.2016.076714\u003c/span\u003e\u003cspan address=\"10.1504/IJPQM.2016.076714\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eSaunders M, Lewis P, Thornhill A (2019) Research methods for business students, 8th edn. Pearson, Harlow, UK\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eSch\u0026ouml;lkopf B (2022) Causality for machine learning. In Probabilistic and Causal Inference; Gefner, H., Dechter, R., Halpern, J.Y., Eds.; ACM, ; Vol. 27, pp. 765\u0026ndash;804\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eStake RE (1995) The art of case study research; Sage Publications: Thousand Oaks, CA, USA\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eKI entwickelt sich in Deutschland nur langsam (2023) Statista. Available online: \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://de.statista.com/infografik/22295/umfrage-zum-einsatz-von-kuenstlicher-intelligenz-in-unternehmen/\u003c/span\u003e\u003cspan address=\"https://de.statista.com/infografik/22295/umfrage-zum-einsatz-von-kuenstlicher-intelligenz-in-unternehmen/\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (accessed on 17 November\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eTalha M (2004) Total quality management (TQM): An overview. Bottom Line 17:15\u0026ndash;19. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1108/08880450410519656\u003c/span\u003e\u003cspan address=\"10.1108/08880450410519656\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eThi\u0026eacute;e (2021) L.W. A systematic literature review of machine learning canvases. In INFORMATIK 2021, Lecture Notes in Informatics\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eTimmermans S, Tavory I (2012) Theory construction in qualitative research: From grounded theory to abductive analysis. Sociol Theory 30:167\u0026ndash;186. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1177/0735275112457914\u003c/span\u003e\u003cspan address=\"10.1177/0735275112457914\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eVan Aken JE (2004) Management research based on the paradigm of the design sciences: The quest for field-tested and grounded technological rules. J Manag Stud 41:219\u0026ndash;246. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1111/j.1467-6486.2004.00430.x\u003c/span\u003e\u003cspan address=\"10.1111/j.1467-6486.2004.00430.x\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003ean de Ven AH (2007) Engaged scholarship: A guide for organizational and social research. Oxford University Press, New York, NY, USA\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eYin RK (2018) Case study research and applications: Design and methods, 6th edn. Sage, Thousand Oaks, CA, USA\u003c/span\u003e\u003c/li\u003e\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":"Quality 5.0, design science research, low-code machine learning, SMEs, operational productivity, sentiment analysis, predictive classification","lastPublishedDoi":"10.21203/rs.3.rs-7839321/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7839321/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThe data-insight gap is persistent among Small and Medium Enterprises (SMEs): most of them generate mass volumes of data about their operations and customers, but fail to use it analytically and convert to actionable intelligence. SMEs of Saudi Arabia, this paper meets this challenge by formulating and discussing a portfolio of four low-code machine-learning (ML) artifacts sentiment analysis, market basket modeling, geospatial clustering, and predictive classification as a Design Science Research (DSR) contribution. Through the Knowledge Discovery in Databases (KDD) process, the models were used to illustrate the applicability of the concept of Quality 5.0 in the Saudi Arabian emergent scuba diving industry: human centricity, operational resilience, and holistic sustainability through operationalization by SMEs. Findings indicate the portfolio facilitates emotional mapping of experience, personalization of the curriculum, planning of sites on safety grounds, and ecological mitigation of risk. This research contributes to the applied literature of Quality 5.0 by making the theoretical constructs practical and experienceable through providing a set of guidelines and interpretation, making it a replicable roadmap of introducing AI on data-heavy service-based small and medium-sized enterprises.\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003cp\u003e\u003c/p\u003e","manuscriptTitle":"The Impact of Machine Learning on Business Productivity: A Comprehensive Study within the Quality 5.0 Framework","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-10-15 05:56:53","doi":"10.21203/rs.3.rs-7839321/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":"437c2535-3c5a-4bab-ba16-9d6dc45b304d","owner":[],"postedDate":"October 15th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-11-13T12:53:46+00:00","versionOfRecord":[],"versionCreatedAt":"2025-10-15 05:56:53","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7839321","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7839321","identity":"rs-7839321","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}