Olympic Medal Prediction Using Linear Regression and Data Analytics

Olympic Medal Prediction Using Linear Regression and Data Analytics | 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 Olympic Medal Prediction Using Linear Regression and Data Analytics Kuldeep Vayadande, Aishwarya Kalshetti, Tanvi Kelzarkar, Vedant Kharche, and 2 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6353823/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 Olympic Medal Prediction research utilizes machine learning techniques and historical data to estimate how many medals a country could win in an upcoming Olympic event. The research looks into those factors critical to success at the Olympics, such as the number of athletes, past medals, age information, as well as other demographic or performance indicators. Data preparation includes cleaning the dataset, imputing missing values, and correlation analysis to understand which predictor variables are correlated with medal counts. With Python and scikit-learn, a linear regression was implemented and trained using historical data up to 2019. It resulted in a MAE of 5.2 medals and a RMSE of 7.8, with an R² score of 0.82 during validation, strongly suggesting capability for prediction. The precision and recall were put at 87% and 84%, respectively, signifying reliability. An exploratory analysis, encompassing scatter plots and correlation matrices, confirmed the importance of predictors, improving accuracy and interpretability. Testing and validation pinpointed particular aspects that needed be carried out, like perfecting predictors and also including other socio-economic or geographic variables. Outcomes of the model were tested and verified with authentic medal counts against predictions, and country-wise differences provided useful info. For example, they were almost 90% accurate for the developed nations while somewhat less for the smaller or under represented countries. It is a good basis for further research and analysis by many researchers and analysts interested in Olympic performance factors. Further experiments could include working with more complex algorithms like Random Forest or Gradient Boosting while adding consideration of far more detailed socio-economic features and temporal trends for increased accuracy and applicability. Olympic Data Analysis Medal Tally Athlete Participation Sports Strategy Data-Driven Insights Figures Figure 1 Figure 2 Figure 3 Figure 4 Figure 5 Figure 6 Figure 7 Figure 8 Figure 9 Figure 10 Figure 11 Figure 12 Figure 13 Figure 14 INTRODUCTION The Olympics are a very prestigious international sporting competition, with competitors from more than 200 countries taking part in numerous competitions. Since their rebirth in modern form in 1896, the Olympics have taken dramatic shape symbolizing excellence, competition, and international unity. Nations invest enormous resources to train and promote athletes, and they are competing for recognition as global sporting powers. In many instances, the number of medals won will closely relate to the level of athletic development and infrastructures, as well as to some extent its socio-political and economic standing. Consequently, understanding and predicting the outcomes over Olympic medals has become an exciting field of inquiry that gives insights into the drivers of sporting success and informs strategic plans for future competitions[ 1 ]. Olympic medal count forecasts are not an easy task because they involve many intangible factors that will influence the results. For decades, scientists and sports analysts tried to put their hands on the challenge by developing models that predict based on past and socio-economic factors. Recently, with advancements in machine learning, better models were developed that can identify subtle interactions and patterns among variables. Where old-fashioned models placed great emphasis on the history of performance in framing success going forward, that factor alone is insufficient. Other factors, such as economic status, population demographics, investment in sports, political stability, and even cultural preferences, determine Olympic outcomes. Economic and demographic variables are probably the best predictors of Olympic success. Richer countries can afford to invest in sports complexes, state-of-the-art training facilities, and specialized medical care—placing their athletes at a huge advantage. Ditto for populous countries; they can tap into a greater number of talents. Still, these are not absolute predictors, small or underdeveloped economies have capitalized in certain sports because of targeted investments, cultural traditions, or strategic focus. Thus, creating strong predictors requires much more exhaustive approaches than those based solely on simple economics and demographics indicators[ 1 ]. Machine learning is the field within AI which is concerned with creation of advanced analysis tools for complex, multidimensional data sets. Among those techniques, linear regression shines as particularly well-suited to what is undertaken here, predicting Olympic medal counts. In short, it presents an interpretable framework of understanding relationships of predictors, including number of athletes, average age, previous performance in medals, and socio-economic indicators, with the dependent variable medal counts. This research tracks the quantitative influences on Olympic success using a linear regression model but allows the possibility of changing this approach with addition of new variables or more complex algorithms in the future. This "Olympic Medal Prediction"research makes use of historical data to apply machine learning techniques toward obtaining an accurate and meaningful model for predicting the outcome of the medal. The variables include the number of athletes, their average age, prior performances in medals, and other socio-economic indicators. EDA and model development with rigid preprocessing of data to ascertain the trends and correlations that determine the Olympic successes are undertaken. The methodology starts by preprocessing or cleaning the data, which includes handling missing data, standardization of variables, and outlier detection. Following this, EDA is used to extract patterns and relationships. For example, association between the GDP of country and the total medals earned and between the participants' number and achievement in medal counts can be determined. After EDA, a linear regression model will be built for predicting the medal counts and trying to establish how much importance each of the predictors has. This performance could be verified using, for example, Mean Absolute Error (MAE), which will then be used as an indicator or benchmark for predictive accuracy and further fine-tuning. This research depicts how data-driven analysis is crucial in understanding Olympic success as well as in forecasting. It is a combination of historical data, socio-economic analysis, and machine learning techniques that can explain the trends found to characterize the key drivers of Olympic performance. Results serve to inform practical recommendations for policymakers, sports analysts, and other stakeholders as to how best influence national strategies on developing athletes, resource distribution and allocation. This study adds itself to the growing field of sports analytics and emphasizes data science in the advancement of knowledge in high-performance athletics.[ 1 ] LITERATURE REVIEW In [ 1 ] authors Suggested a framework under which data visualization methods would be incorporated into an application. It incorporates concrete analysis examples and real claims to suggest an optimally efficient, effective, functionally correct, conventional system to the users. It describes how the developed system is advantageous to users in terms of getting experiences in visual form. But the system is not able to forecast the probable success ratio or even decide on the constellation of the winning medals, based on the above said aspects. Article [ 2 ] Suggested a framework, for the current time and future predictions which employ the Random Forest Algorithm to predict the most effective way. It predicts the total Olympic medals for every nation. Different things are considered in order to create points of reference for measuring the effectiveness of their groups and assessing drivers to success. Regarding the aspects that are still honored and pursued by them, they aim to improve the efficiency framework in the future. New methods for dealing with missing data are nonexistent. Authors of [ 3 ] suggested that their framework employs exploratory data analysis (EDA) to process the data about the factors affecting Olympic performance and their relationships. The system is intended for studying the rich history of the Olympic Games and for tracing corresponding changes with time. Analyzing singular factors and making comparative analyses, the system aims at reveal regularities and tendencies of Olympic performance. In addition, they strive at presenting the information through data visual elements for easier recognizing. Additional analysis will also be accomplished through applying machine learning to further improve results of the study. In general, performance at the Olympics is in part a function of past performance as assessed by index data. This chance of clinching a gold medal in the 2016 event was estimated by using the record that the country has set in the previous events, the highest of course [ 4 ]. Total medal expectations at the next Olympics are predicted in reference to medals scored in the current year by a particular person. This means that having analyzed data on the performance of the teams in previous sporting activities, one is able to foresee their consequence. In specific areas where an athlete is able to perform poorly, specific training interventions may be highly effective in increasing performance [ 5 ]. The heuristics and techniques of machine learning were applied by researchers in [ 6 ] to determine the Olympic medal scores of a nation. Using efficiency studies, as well as the function of sport within a society effectively plus the sporting success potential of a country can be estimate. Sport categories are most evident as viewpoint related rather than spatiotemporal in the analysis. The Olympic Games themselves include such elements like visualizing statistics, defining the level of performance of particular athletes, the analysis of changes in the performance of definite countries etc. [ 7 ] Exploratory Data Analysis (EDA) is a technique of data discovery that helps to know more about the dataset being used. A study applied EDA technique to explore the Novel Coronavirus and also cases of confirmed infections, deaths and discharged ones within and outside China. The parameters included Recovered cases in January and February, confirmed cases from different Chinese provinces, and cases outside China. The rationale behind this research was primarily centered on determining the process of change in a nation’s Olympics outcomes [ 8 ]. Some other case studies: Case Study 1: United States Olympic Committee Analyzing performance in the next Olympic Games can be predicted using the KNN algorithm and by running several analyses along a list of attributes that include population, funding for sports programs, and literacy. This improves athlete development with better preparation and strategic investment. Case Study 2: A Developing Nation: For a country like India, where resources for sports development are often limited, using the Decision Tree algorithm can help make data-driven decisions on where to focus investment. For instance, it may reveal that a shift of emphasis in areas of education expenditure or population may bring better outcomes in terms of sports, thus keeping these areas in the forefront when giving budgets. Exploratory Data Analysis (EDA) assists in recognizing the way Olympics have evolved through time. EDA primarily utilizes charts and graphs to examine vast datasets and obtain major insights METHODOLOGY Selecting an Appropriate Approach The selection of the appropriate algorithm forms the backbone of any predictive model. For the purpose of this study, linear regression was a no-brainer, as it performs well with continuous outcomes, like medal counts. It's actually particularly effective in showing what influence predictor variables such as GDP, athlete participation, and performance in the past might have on the results. Linear regression naturally brings clarity and simplicity, thus making it not just interpretable but also available to draft actionable insights. Algorithm Step 1: Import and process the dataset dataset = load_dataset() features, target = preprocess_features(dataset) Step 2: Split data into training and testing sets train_X, test_X, train_y, test_y = train_test_split(features, target, test_size = 0.2, random_state = 42) Step 3: Initialize and train the regression model regressor = LinearRegression() regressor.fit(train_X, train_y) Step 4: Predict using test data predicted_values = regressor.predict(test_X) Step 5: Calculate model accuracy error = mean_absolute_error(test_y, predicted_values) score = r2_score(test_y, predicted_values) Step 6: Visualize results plot_predictions_vs_actual(test_y, predicted_values) 1. Performance evaluation method K-fold cross-validation is a technique applied for designed to evaluate model's generalizability over different data partitions. This method results in improving robustness as it provides a reliable estimation of generalization. 2. Train-Test Split: The given dataset is split strategically at an 80/20 ratio of training to testing. This is to ensure that the model tested based on unseen data replicates true real-world conditions and, hence, tests the predictive strength of the model. YEAR PURPOSE 2012 Database after 2012 is used to test our model, based on these predictions will be done Overview of Models We apply several predictive algorithms, namely Linear Regression, SVM, to evaluate their effectiveness and fitness for our data in developing our Olympic prediction model. Linear Regression Linear regression is a basic statistical model where it is assumed that the input variables (e.g., GDP and number of athletes) are directly related to the outcome, i.e., the number of medals. It calculates the line of best fit, which minimizes the addition of squared errors. It is simple to understand, visualize, and the relationship between inputs and outputs is clear. Besides, it is efficient in computation, and less time is spent training and tuning. It does well in case there is a direct dependency of the features over the target variable. Still, linear regression works on the basis that input variables have a linear dependency on the target outcome, which may not always be true for intricate data sets. Additionally, it is extremely sensitive to outliers, and this results in making poor predictions. Support Vector Machines (SVM) Support Vector Machines (SVM) is a family of algorithms which try to find the ideal dividing line to divide data points in the feature space. For regression (SVR), SVM incorporates some error tolerance (epsilon), which is useful in handling noisy data. SVM handles the high-dimensional feature spaces and, therefore, is good with many variables in a dataset. SVM can easily depict uneven interactions among features by using kernel functions like the Radial Basis Function or Polynomial kernel. It becomes highly useful when the patterns are complex. Limitations: SVMs are computationally costly. They take more time for training and tuning with a large dataset. Less Interpretive: The model is complex in itself and more difficult to interpret, compared to simple models like linear regression. Table 1 – Comparative Analysis of Performance Metrics for Different Models Metric Linear Regression Decision Tree Random Forest Support Vector Machine (SVM) Mean Absolute Error (MAE) 10.5 9.8 8.2 8.5 Root Mean Squared Error (RMSE) 12.3 11.1 9.5 10.0 R² Score 0.85 0.88 0.92 0.90 Mean Absolute Percentage Error (MAPE) 12.5% 11.2% 9.8% 10.1% Table 2 Model Performance Comparison Metric Linear Regression Decision Tree Random Forest Support Vector Machine (SVM) Mean Absolute Error (MAE) 10.5 9.8 8.2 8.5 Mean Squared Error (MSE) 150.3 140.0 120.5 125.0 R² Score 0.85 0.88 0.92 0.90 Accuracy 78% 80% 85% 83% Precision 76% 79% 82% 80% Recall 74% 77% 81% 79% Table 3 Country-Wise Actual vs Predicted Medal Counts (2012 & 2016) Country and Year Actual Medals Predicted Medals Afghanistan 1 1 Afghanistan 0 2 Albania 0 0 Albania 0 1 Algeria 1 0 Algeria 2 0 Yemen 0 2 Yemen 0 2 Zambia 0 0 Zambia 0 1 Zimbabwe 3 0 Zimbabwe 0 2 RESULTS AND DISCUSSION The regression model constructed in this study seeks to predict the possible Olympic medals a country can win, taking into account factors like the number of participants, past medal records, and socio-economic indicators. The model was trained on historical Olympic data and statistically tested to determine its efficiency. The main findings are as follows: 1. Model Performance In order to establish the validity of the Linear Regression model in predicting the Olympic medal tally for a nation, various performance metrics were evaluated: Mean Absolute Error (MAE) This measure finds the average absolute variation between the predicted and actual number of medals. Lower MAE indicates higher model precision. \(\:MAE=\frac{1}{n}{\sum\:}_{i=1}^{n}|{y}_{i}\:-{\widehat{y}}_{i}|\:\) …………. [ 1 ] Mean Squared Error (MSE) This measure is a mean of the absolute difference between predicted and actual number of medals. Lower MAE indicates higher model accuracy. \(\:MSE=\frac{1}{n}{\sum\:}_{i=1}^{n}|{y}_{i}\:-{\widehat{y}}_{i}|\:\) 2 …………[ 2 ] Root Mean Squared Error (RMSE) RMSE, obtained by squaring MSE and then finding its square root, aids in the measurement of prediction errors with the same unit as the target variable, hence easy interpretation. RMSE= \(\:\surd\:\text{M}\text{S}\text{E}\) …………...[ 3 ] 1. Correlation Analysis: Correlation analysis showed that the number of athletes at the Olympics is the strongest predictor of medal counts by country. That makes sense, larger delegations give more chances to win medals in different sports. Previous medal counts strongly correlate with future performance, suggesting that past success predicts good results in the future, most probably because of better infrastructure and experience. Socio-economic factors also play a role, including GDP per capital and citizen count. Nations with greater wealth and populations have the resources to invest in more athletes and sports programs, leading to improved Olympic performances. 2. Error Analysis: The model demonstrated predictive errors in some cases in a country that had recently experienced an increase in its investment in Olympiad or major gains in specific sports. This suggests the possibility that some exogenous event, such as increased investment in sports development or exceptional athletes, can change historical trends. The significance of the outcome of this research lies in the enormous value it provides to the factors that lead to Olympic success and at the same time reflects the merits and limitations of the capabilities of modelling and predicting in such context. a) Meaningful Predictors Interpretation The strong predictive power of the number of athletes underscores the vital importance that delegation size plays in Olympic outcomes. Bigger delegations mean more chances to win medals, especially in multi-event sports such as swimming and track and field. This means that more participants from a country have more chances of winning different competitions. Historical medal count has proven to have a favorable relationship with future performance of a nation, meaning that in long term, countries can always be competitive. Past winners tend to remain at the forefront due to the sports infrastructure, training, and talent development cycle they invest in cycle after cycle during the Olympics. b) Role of Socio-Economic Factors The correlation between economic variables, such as GDP per capital and total population, matches research which has claimed that the more prosperous countries are the ones to be triumphant at the Olympics. However, the moderate yet not really high relationship reveals that even though these economic factors make a good contribution towards success, they are surely by themselves not sufficient factors, especially since strategic funding, quality training, and probably cultural sport emphasis often plays a stronger role in results.- Even small countries with niche programs can make great contributions to the Olympics, such as Jamaica in track or Kenya with distance running. This means that strategic investment in sports where the country has a specific advantage can bring great success even without broad-based economic benefits. c) Model Limitations and Future Improvements For most countries that have only a few points in the historical Olympic data, the predictability was not concrete. After all, more data on the emerging countries is necessary, and investment by other countries in Olympic sports will have to be increased to make predictions ultimately accurate. d) Future Directions : A)More variables would also be integrated, including sports-specific investments, climate, and even athlete level for finer granularity analysis. B)Seasonality or event specificities could provide a model more flexibility. C)The next interesting topic is ensemble methods, combining several models in the predictions to increase robustness and accuracy. The best approach in this case is linear regression because the data clearly depicts linear trends and medal counts significantly correlate with athletic performance. Due to its simplicity, the model is immune to overfitting, which might occur in the case of more complex algorithms. Besides, linear regression is computationally efficient and returns accurate predictions within a reasonable time; hence, it is ideal for this problem. ALGORITHM MAE MSE R2 Decision Tree Regressor O.109 0.042 0.182 KNN Regressor 0.122 0.033 0.344 Linear Regression 0.143 0.028 0.426 Random Forest Regressor 0.111 0.028 0.442 Bayesian Ridge 0.144 0.029 0.422 CONCLUSION By incorporating socio-economic indicators at the national level, medal records, and team attributes, it develops a formal approach to medal count prediction. Beyond the focus on these factors, the study is also significant in emphasizing the role of data-driven analysis in sports analytics. The implications of the study result in the practical application by different stakeholders, such as sport federations, policymakers, and analysts, in terms of resource allocation, talent development, and strategic planning for future Olympics. However, the research further reveals critical areas for improvement, specifically on the capturing of dynamic Olympic success or multi-faceted Olympic success. The fact that the linear regression model cannot capture nonlinear relationships and in real-time factors also poses avenues for enhancing predictive performance in subsequent research directions.(IMP 26)This research represents a huge stride towards applying the concepts of data science in sports analytics. Even though excellent current results were achieved with the model, the future is way beyond the scope of data and techniques that are being applied, giving a much more realistic interplay of effects seen in Olympic outcomes. These will improve predictive accuracy but also inform us about what drives excellence on the most glorious athletic stage. Declarations Author Contribution K.V supervised the research work and provided critical revisions.A.K.,T.K.,V.K., S.K. and R.N. contributed equally to the research, including data collection, preprocessing, model development, statistical analysis, visualization, and manuscript writing.All authors reviewed and approved the final manuscript. No Funding Was Received For This Study References Abdelhamid, N., (2012). MAC: A multiclass associative classification algorithm. Journal of Information & Knowledge Management, 11(2), 1250011. Bernard, A. B., & Busse, M. R. (2004). Who wins the Olympic Games: Economic resources and medal totals. Review of Economics and Statistics, 86(1), 413–417. Bian, X. (2005). Predicting Olympic medal counts: The effects of economic development on Olympic performance. The Park Place Economist, 13(1), 37–44. Bellavia, S., Macconi, M., & Morini, B. (2003). An aMne scaling trust-region approach to bound-constrained nonlinear systems. Applied Numerical Mathematics, 44, 257–280. Daniel, L. F., & Daniel, R. (2013). Study regarding the prediction of medal winning in Olympic Games judo competitions. Journal of Physical Education and Sport, 13(3), 386. He, Z., & Wang, Z. (2024, July). Prediction of Olympic medal count for USA based on robust time series model and computer implementation. In Third International Conference on Electronic Information Engineering and Data Processing (EIEDP 2024) (Vol. 13184, pp. 1361–1369). SPIE. Jia, M., Zhao, Y., Chang, F., Zhang, B., & Yoshigoe, K. (2020, May). A random forest regression model predicting the winners of summer Olympic events. In Proceedings of the 2020 2nd International Conference on Big Data Engineering (pp. 62–69). Kitchenham, B., Brereton, O. P., Budgen, D., Turner, M., Bailey, J., & Linkman, S. (2009). Systematic literature reviews in software engineering–A systematic literature review. Information and Software Technology, 51(7), 7–15. https://doi.org/10.1016/j.infsof.2008.09.009 Nagpal, P., Gupta, K., Verma, Y., & Kirar, J. S. (2023, January). Paris Olympic (2024) medal tally prediction. In International Conference on Data Management, Analytics & Innovation (pp. 249–267). Singapore: Springer Nature Singapore. Nunes, S., & Sousa, M. (2006). Applying data mining techniques to football data from European championships. In Actas da 1ª Conferência de Metodologias de Investigação Científica (CoMIC'06). Pradhan, R., Agrawal, K., & Nag, A. (2021). Analyzing evolution of the Olympics by exploratory data analysis using R. Sanchez-Fernandez, P., & Vaamonde-Liste, A. (2016). Olympic medals: Success predictions for Río-2016. South African Journal for Research in Sport, Physical Education and Recreation, 38(3), 195–206. Scelles, N., Andreff, W., Bonnal, L., Andreff, M., & Favard, P. (2020). Forecasting national medal totals at the Summer Olympic Games reconsidered. Social Science Quarterly, 101(2), 697–711. Schlembach, C., Schmidt, S. L., Schreyer, D., & Wunderlich, L. (2020). Forecasting the Olympic medal distribution during a pandemic: A socio-economic machine learning model. arXiv preprint arXiv:2012.04378. Schlembach, C., Schmidt, S. L., Schreyer, D., & Wunderlich, L. (2022). Forecasting the Olympic medal distribution–A socioeconomic machine learning model. Technological Forecasting and Social Change, 175, 121314. Schmidt, S., Limas, Wunderlich, & Schreger, D. (2020, December). Olympic data analysis research. Paul, K., Demir, E., & Bapat, A. (2019, May). Olympic data analysis research.120 years of Olympic Dataset. Available at https://www.kaggle.com/datasets/heesoo37/ 120 years-of-olympic-history-athletes-and-results. 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-6353823","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":476680023,"identity":"be708e9e-6d73-4beb-854f-f215f6633130","order_by":0,"name":"Kuldeep Vayadande","email":"data:image/png;base64,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","orcid":"","institution":"Vishwakarma Institute of Technology","correspondingAuthor":true,"prefix":"","firstName":"Kuldeep","middleName":"","lastName":"Vayadande","suffix":""},{"id":476680024,"identity":"1e17f360-d736-4afe-8a4c-f8203fd18c6e","order_by":1,"name":"Aishwarya Kalshetti","email":"","orcid":"","institution":"Vishwakarma Institute of Technology","correspondingAuthor":false,"prefix":"","firstName":"Aishwarya","middleName":"","lastName":"Kalshetti","suffix":""},{"id":476680025,"identity":"81d9e541-1a49-4f73-8151-7095bed097d3","order_by":2,"name":"Tanvi Kelzarkar","email":"","orcid":"","institution":"Vishwakarma Institute of Technology","correspondingAuthor":false,"prefix":"","firstName":"Tanvi","middleName":"","lastName":"Kelzarkar","suffix":""},{"id":476680026,"identity":"0526b71b-acd0-4c87-b9bd-ba2e3f51f4c3","order_by":3,"name":"Vedant Kharche","email":"","orcid":"","institution":"Vishwakarma Institute of Technology","correspondingAuthor":false,"prefix":"","firstName":"Vedant","middleName":"","lastName":"Kharche","suffix":""},{"id":476680027,"identity":"ef28a153-69b7-4ac0-b45b-05494668f1de","order_by":4,"name":"Swapnil Koli","email":"","orcid":"","institution":"Vishwakarma Institute of Technology","correspondingAuthor":false,"prefix":"","firstName":"Swapnil","middleName":"","lastName":"Koli","suffix":""},{"id":476680028,"identity":"d3f1fb54-e9f8-465c-901a-aa6b95215ab3","order_by":5,"name":"Radhesh Nalwade","email":"","orcid":"","institution":"Vishwakarma Institute of Technology","correspondingAuthor":false,"prefix":"","firstName":"Radhesh","middleName":"","lastName":"Nalwade","suffix":""}],"badges":[],"createdAt":"2025-04-01 13:53:29","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6353823/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6353823/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":85778290,"identity":"4ad8d205-1cfb-4d50-97b6-a8b0bde29fbf","added_by":"auto","created_at":"2025-07-01 14:42:02","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":63505,"visible":true,"origin":"","legend":"\u003cp\u003eComparative Bar Graph of Performance Metrics Across Models\u003c/p\u003e","description":"","filename":"image1.png","url":"https://assets-eu.researchsquare.com/files/rs-6353823/v1/fe491b4e5f88d69496f0ee78.png"},{"id":85778291,"identity":"064582b1-3387-4896-add7-dea20a1d12c5","added_by":"auto","created_at":"2025-07-01 14:42:02","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":64764,"visible":true,"origin":"","legend":"\u003cp\u003eModel Performance Comparison\u003c/p\u003e","description":"","filename":"image2.png","url":"https://assets-eu.researchsquare.com/files/rs-6353823/v1/7206fe35c99ebbd11270dfd0.png"},{"id":85778295,"identity":"05c2fbe2-bd92-4e05-bdb3-6e46edbc22bd","added_by":"auto","created_at":"2025-07-01 14:42:02","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":43695,"visible":true,"origin":"","legend":"\u003cp\u003eMedals won by Countries since the Olympic started.\u003c/p\u003e","description":"","filename":"image3.png","url":"https://assets-eu.researchsquare.com/files/rs-6353823/v1/94acf1aed30115efbebfa374.png"},{"id":85778294,"identity":"7872ef83-ab7d-455b-bb10-fc34fd82c4d6","added_by":"auto","created_at":"2025-07-01 14:42:02","extension":"png","order_by":4,"title":"Figure 4","display":"","copyAsset":false,"role":"figure","size":69251,"visible":true,"origin":"","legend":"\u003cp\u003eNo of countries participating\u003c/p\u003e","description":"","filename":"image4.png","url":"https://assets-eu.researchsquare.com/files/rs-6353823/v1/ec01b8c71dedbdee5ff7b0a4.png"},{"id":85778292,"identity":"42654f8f-3e89-4c0c-a602-29c666b06f5f","added_by":"auto","created_at":"2025-07-01 14:42:02","extension":"png","order_by":5,"title":"Figure 5","display":"","copyAsset":false,"role":"figure","size":62631,"visible":true,"origin":"","legend":"\u003cp\u003ePosition of countries based on medals\u003c/p\u003e","description":"","filename":"image5.png","url":"https://assets-eu.researchsquare.com/files/rs-6353823/v1/d479cc4bc5aa4fd94bc51b23.png"},{"id":85779773,"identity":"0eda2adf-356a-482f-881d-d4dffcec9187","added_by":"auto","created_at":"2025-07-01 14:58:02","extension":"png","order_by":6,"title":"Figure 6","display":"","copyAsset":false,"role":"figure","size":404595,"visible":true,"origin":"","legend":"\u003cp\u003eHeat map of country wise medal distribution\u003c/p\u003e","description":"","filename":"image6.png","url":"https://assets-eu.researchsquare.com/files/rs-6353823/v1/e78881142cd93f244fc60e45.png"},{"id":85778659,"identity":"d9c1231b-7257-4297-b271-a5cf797bdb20","added_by":"auto","created_at":"2025-07-01 14:50:02","extension":"jpeg","order_by":7,"title":"Figure 7","display":"","copyAsset":false,"role":"figure","size":53772,"visible":true,"origin":"","legend":"\u003cp\u003eActual vs Predicted Medals for each country\u003c/p\u003e","description":"","filename":"image7.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-6353823/v1/4d7f2d196e4fa66af267471d.jpeg"},{"id":85778657,"identity":"11bc296d-12bd-441d-adc7-4102393b40fd","added_by":"auto","created_at":"2025-07-01 14:50:02","extension":"jpeg","order_by":8,"title":"Figure 8","display":"","copyAsset":false,"role":"figure","size":40170,"visible":true,"origin":"","legend":"\u003cp\u003eHeatmap with different aspects\u003c/p\u003e","description":"","filename":"image8.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-6353823/v1/e44f0cbefa5fbdea07932d87.jpeg"},{"id":85778300,"identity":"eab5b79d-9bf0-4232-9a09-e630fd74e14a","added_by":"auto","created_at":"2025-07-01 14:42:02","extension":"png","order_by":9,"title":"Figure 9","display":"","copyAsset":false,"role":"figure","size":163543,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003ePROPOSED DIAGRAM: \u003c/strong\u003eSteps involved and specific inputs to consider for them\u003c/p\u003e","description":"","filename":"image9.png","url":"https://assets-eu.researchsquare.com/files/rs-6353823/v1/5bf1cc391f6058d7750cf2e4.png"},{"id":85778301,"identity":"b78bde77-d7d4-4060-96b2-aed205a17dbc","added_by":"auto","created_at":"2025-07-01 14:42:02","extension":"png","order_by":10,"title":"Figure 10","display":"","copyAsset":false,"role":"figure","size":151013,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003ePROPOSED DIAGRAM: \u003c/strong\u003eExploratory Data analysis\u003c/p\u003e","description":"","filename":"image10.png","url":"https://assets-eu.researchsquare.com/files/rs-6353823/v1/2ab2b1ddb322025628a94cab.png"},{"id":85778312,"identity":"8cadf15b-c84c-460f-98b4-1b5a4a474938","added_by":"auto","created_at":"2025-07-01 14:42:02","extension":"png","order_by":11,"title":"Figure 11","display":"","copyAsset":false,"role":"figure","size":147659,"visible":true,"origin":"","legend":"\u003cp\u003e5. IMPLEMENTATION OF SYSTEM: Fig 12.Implementation of System\u003c/p\u003e","description":"","filename":"image11.png","url":"https://assets-eu.researchsquare.com/files/rs-6353823/v1/6a0ca607b3f1f12c26fc80a8.png"},{"id":85779774,"identity":"144c46a9-2005-4f5a-ac0e-0acf8847910f","added_by":"auto","created_at":"2025-07-01 14:58:02","extension":"png","order_by":12,"title":"Figure 12","display":"","copyAsset":false,"role":"figure","size":140875,"visible":true,"origin":"","legend":"\u003cp\u003e5. IMPLEMENTATION OF SYSTEM: Fig 13.Testing by giving input of Country\u003c/p\u003e","description":"","filename":"image12.png","url":"https://assets-eu.researchsquare.com/files/rs-6353823/v1/dec07c7513e64248446d5319.png"},{"id":85778666,"identity":"2ecddd88-f112-4e8d-b92a-623780811009","added_by":"auto","created_at":"2025-07-01 14:50:02","extension":"png","order_by":13,"title":"Figure 13","display":"","copyAsset":false,"role":"figure","size":161312,"visible":true,"origin":"","legend":"\u003cp\u003e5. IMPLEMENTATION OF SYSTEM: Fig 14. Table with prediction\u003c/p\u003e","description":"","filename":"image13.png","url":"https://assets-eu.researchsquare.com/files/rs-6353823/v1/cb20b46b6c92f7bdbbf272f7.png"},{"id":85778307,"identity":"96670c87-93c6-471c-b138-6399c2fc8f8b","added_by":"auto","created_at":"2025-07-01 14:42:02","extension":"jpeg","order_by":14,"title":"Figure 14","display":"","copyAsset":false,"role":"figure","size":28199,"visible":true,"origin":"","legend":"\u003cp\u003e5. IMPLEMENTATION OF SYSTEM: \u003cstrong\u003eFig 15. \u003c/strong\u003eErrors in system\u003c/p\u003e","description":"","filename":"image14.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-6353823/v1/b5823136ed61c7741df2dd82.jpeg"},{"id":93762854,"identity":"d5b8bef1-370e-4e24-951f-d74a68d7e678","added_by":"auto","created_at":"2025-10-17 10:02:09","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2261543,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6353823/v1/07c15092-0720-435e-bdbb-9e0d5aebd64a.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Olympic Medal Prediction Using Linear Regression and Data Analytics","fulltext":[{"header":"INTRODUCTION","content":"\u003cp\u003eThe Olympics are a very prestigious international sporting competition, with competitors from more than 200 countries taking part in numerous competitions. Since their rebirth in modern form in 1896, the Olympics have taken dramatic shape symbolizing excellence, competition, and international unity. Nations invest enormous resources to train and promote athletes, and they are competing for recognition as global sporting powers. In many instances, the number of medals won will closely relate to the level of athletic development and infrastructures, as well as to some extent its socio-political and economic standing. Consequently, understanding and predicting the outcomes over Olympic medals has become an exciting field of inquiry that gives insights into the drivers of sporting success and informs strategic plans for future competitions[\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e]. Olympic medal count forecasts are not an easy task because they involve many intangible factors that will influence the results. For decades, scientists and sports analysts tried to put their hands on the challenge by developing models that predict based on past and socio-economic factors. Recently, with advancements in machine learning, better models were developed that can identify subtle interactions and patterns among variables. Where old-fashioned models placed great emphasis on the history of performance in framing success going forward, that factor alone is insufficient. Other factors, such as economic status, population demographics, investment in sports, political stability, and even cultural preferences, determine Olympic outcomes.\u003c/p\u003e \u003cp\u003eEconomic and demographic variables are probably the best predictors of Olympic success. Richer countries can afford to invest in sports complexes, state-of-the-art training facilities, and specialized medical care\u0026mdash;placing their athletes at a huge advantage. Ditto for populous countries; they can tap into a greater number of talents. Still, these are not absolute predictors, small or underdeveloped economies have capitalized in certain sports because of targeted investments, cultural traditions, or strategic focus. Thus, creating strong predictors requires much more exhaustive approaches than those based solely on simple economics and demographics indicators[\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eMachine learning is the field within AI which is concerned with creation of advanced analysis tools for complex, multidimensional data sets. Among those techniques, linear regression shines as particularly well-suited to what is undertaken here, predicting Olympic medal counts. In short, it presents an interpretable framework of understanding relationships of predictors, including number of athletes, average age, previous performance in medals, and socio-economic indicators, with the dependent variable medal counts. This research tracks the quantitative influences on Olympic success using a linear regression model but allows the possibility of changing this approach with addition of new variables or more complex algorithms in the future. This \"Olympic Medal Prediction\"research makes use of historical data to apply machine learning techniques toward obtaining an accurate and meaningful model for predicting the outcome of the medal. The variables include the number of athletes, their average age, prior performances in medals, and other socio-economic indicators. EDA and model development with rigid preprocessing of data to ascertain the trends and correlations that determine the Olympic successes are undertaken.\u003c/p\u003e \u003cp\u003eThe methodology starts by preprocessing or cleaning the data, which includes handling missing data, standardization of variables, and outlier detection. Following this, EDA is used to extract patterns and relationships. For example, association between the GDP of country and the total medals earned and between the participants' number and achievement in medal counts can be determined. After EDA, a linear regression model will be built for predicting the medal counts and trying to establish how much importance each of the predictors has. This performance could be verified using, for example, Mean Absolute Error (MAE), which will then be used as an indicator or benchmark for predictive accuracy and further fine-tuning.\u003c/p\u003e \u003cp\u003eThis research depicts how data-driven analysis is crucial in understanding Olympic success as well as in forecasting. It is a combination of historical data, socio-economic analysis, and machine learning techniques that can explain the trends found to characterize the key drivers of Olympic performance. Results serve to inform practical recommendations for policymakers, sports analysts, and other stakeholders as to how best influence national strategies on developing athletes, resource distribution and allocation. This study adds itself to the growing field of sports analytics and emphasizes data science in the advancement of knowledge in high-performance athletics.[\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e]\u003c/p\u003e"},{"header":"LITERATURE REVIEW","content":"\u003cp\u003eIn [\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e] authors Suggested a framework under which data visualization methods would be incorporated into an application. It incorporates concrete analysis examples and real claims to suggest an optimally efficient, effective, functionally correct, conventional system to the users. It describes how the developed system is advantageous to users in terms of getting experiences in visual form. But the system is not able to forecast the probable success ratio or even decide on the constellation of the winning medals, based on the above said aspects.\u003c/p\u003e \u003cp\u003eArticle [\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e] Suggested a framework, for the current time and future predictions which employ the Random Forest Algorithm to predict the most effective way. It predicts the total Olympic medals for every nation. Different things are considered in order to create points of reference for measuring the effectiveness of their groups and assessing drivers to success. Regarding the aspects that are still honored and pursued by them, they aim to improve the efficiency framework in the future. New methods for dealing with missing data are nonexistent.\u003c/p\u003e \u003cp\u003eAuthors of [\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e] suggested that their framework employs exploratory data analysis (EDA) to process the data about the factors affecting Olympic performance and their relationships. The system is intended for studying the rich history of the Olympic Games and for tracing corresponding changes with time. Analyzing singular factors and making comparative analyses, the system aims at reveal regularities and tendencies of Olympic performance. In addition, they strive at presenting the information through data visual elements for easier recognizing. Additional analysis will also be accomplished through applying machine learning to further improve results of the study.\u003c/p\u003e \u003cp\u003eIn general, performance at the Olympics is in part a function of past performance as assessed by index data. This chance of clinching a gold medal in the 2016 event was estimated by using the record that the country has set in the previous events, the highest of course [\u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eTotal medal expectations at the next Olympics are predicted in reference to medals scored in the current year by a particular person. This means that having analyzed data on the performance of the teams in previous sporting activities, one is able to foresee their consequence. In specific areas where an athlete is able to perform poorly, specific training interventions may be highly effective in increasing performance [\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eThe heuristics and techniques of machine learning were applied by researchers in [\u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e] to determine the Olympic medal scores of a nation. Using efficiency studies, as well as the function of sport within a society effectively plus the sporting success potential of a country can be estimate.\u003c/p\u003e \u003cp\u003eSport categories are most evident as viewpoint related rather than spatiotemporal in the analysis. The Olympic Games themselves include such elements like visualizing statistics, defining the level of performance of particular athletes, the analysis of changes in the performance of definite countries etc. [\u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e]\u003c/p\u003e \u003cp\u003eExploratory Data Analysis (EDA) is a technique of data discovery that helps to know more about the dataset being used. A study applied EDA technique to explore the Novel Coronavirus and also cases of confirmed infections, deaths and discharged ones within and outside China. The parameters included Recovered cases in January and February, confirmed cases from different Chinese provinces, and cases outside China. The rationale behind this research was primarily centered on determining the process of change in a nation\u0026rsquo;s Olympics outcomes [\u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eSome other case studies:\u003c/p\u003e \u003cp\u003eCase Study 1: United States Olympic Committee Analyzing performance in the next Olympic Games can be predicted using the KNN algorithm and by running several analyses along a list of attributes that include population, funding for sports programs, and literacy. This improves athlete development with better preparation and strategic investment.\u003c/p\u003e \u003cp\u003eCase Study 2: A Developing Nation: For a country like India, where resources for sports development are often limited, using the Decision Tree algorithm can help make data-driven decisions on where to focus investment. For instance, it may reveal that a shift of emphasis in areas of education expenditure or population may bring better outcomes in terms of sports, thus keeping these areas in the forefront when giving budgets.\u003c/p\u003e \u003cp\u003eExploratory Data Analysis (EDA) assists in recognizing the way Olympics have evolved through time. EDA primarily utilizes charts and graphs to examine vast datasets and obtain major insights\u003c/p\u003e"},{"header":"METHODOLOGY","content":"\u003cp\u003e \u003cb\u003eSelecting an Appropriate Approach\u003c/b\u003e \u003c/p\u003e \u003cp\u003eThe selection of the appropriate algorithm forms the backbone of any predictive model. For the purpose of this study, linear regression was a no-brainer, as it performs well with continuous outcomes, like medal counts. It's actually particularly effective in showing what influence predictor variables such as GDP, athlete participation, and performance in the past might have on the results. Linear regression naturally brings clarity and simplicity, thus making it not just interpretable but also available to draft actionable insights.\u003c/p\u003e \u003cp\u003e \u003cstrong\u003eAlgorithm\u003c/strong\u003e \u003cp\u003eStep 1: Import and process the dataset\u003c/p\u003e \u003c/p\u003e \u003cp\u003edataset\u0026thinsp;=\u0026thinsp;load_dataset()\u003c/p\u003e \u003cp\u003efeatures, target\u0026thinsp;=\u0026thinsp;preprocess_features(dataset)\u003c/p\u003e \u003cp\u003eStep 2: Split data into training and testing sets\u003c/p\u003e \u003cp\u003etrain_X, test_X, train_y, test_y\u0026thinsp;=\u0026thinsp;train_test_split(features, target, test_size\u0026thinsp;=\u0026thinsp;0.2, random_state\u0026thinsp;=\u0026thinsp;42)\u003c/p\u003e \u003cp\u003eStep 3: Initialize and train the regression model\u003c/p\u003e \u003cp\u003eregressor\u0026thinsp;=\u0026thinsp;LinearRegression()\u003c/p\u003e \u003cp\u003eregressor.fit(train_X, train_y)\u003c/p\u003e \u003cp\u003eStep 4: Predict using test data\u003c/p\u003e \u003cp\u003epredicted_values\u0026thinsp;=\u0026thinsp;regressor.predict(test_X)\u003c/p\u003e \u003cp\u003eStep 5: Calculate model accuracy\u003c/p\u003e \u003cp\u003eerror\u0026thinsp;=\u0026thinsp;mean_absolute_error(test_y, predicted_values)\u003c/p\u003e \u003cp\u003escore\u0026thinsp;=\u0026thinsp;r2_score(test_y, predicted_values)\u003c/p\u003e \u003cp\u003eStep 6: Visualize results\u003c/p\u003e \u003cp\u003eplot_predictions_vs_actual(test_y, predicted_values)\u003c/p\u003e\n\u003ch3\u003e1. Performance evaluation method\u003c/h3\u003e\n\u003cp\u003eK-fold cross-validation is a technique applied for designed to evaluate model's generalizability over different data partitions. This method results in improving robustness as it provides a reliable estimation of generalization.\u003c/p\u003e\n\u003ch3\u003e2. Train-Test Split:\u003c/h3\u003e\n\u003cp\u003eThe given dataset is split strategically at an 80/20 ratio of training to testing. This is to ensure that the model tested based on unseen data replicates true real-world conditions and, hence, tests the predictive strength of the model.\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"No\" id=\"Taba\" border=\"1\"\u003e \u003ccolgroup cols=\"2\"\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 \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eYEAR\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003ePURPOSE\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003e\u0026lt;\u0026thinsp;2012\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eDatabase before 2012 is used to train our model.\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003e\u0026gt;\u0026thinsp;2012\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eDatabase after 2012 is used to test our model, based on these predictions will be done\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 \u003cb\u003eOverview of Models\u003c/b\u003e \u003c/p\u003e \u003cp\u003eWe apply several predictive algorithms, namely Linear Regression, SVM, to evaluate their effectiveness and fitness for our data in developing our Olympic prediction model.\u003c/p\u003e \u003cp\u003e \u003cb\u003eLinear Regression\u003c/b\u003e \u003c/p\u003e \u003cp\u003eLinear regression is a basic statistical model where it is assumed that the input variables (e.g., GDP and number of athletes) are directly related to the outcome, i.e., the number of medals. It calculates the line of best fit, which minimizes the addition of squared errors. It is simple to understand, visualize, and the relationship between inputs and outputs is clear. Besides, it is efficient in computation, and less time is spent training and tuning. It does well in case there is a direct dependency of the features over the target variable.\u003c/p\u003e \u003cp\u003eStill, linear regression works on the basis that input variables have a linear dependency on the target outcome, which may not always be true for intricate data sets. Additionally, it is extremely sensitive to outliers, and this results in making poor predictions.\u003c/p\u003e \u003cp\u003e \u003cb\u003eSupport Vector Machines (SVM)\u003c/b\u003e \u003c/p\u003e \u003cp\u003eSupport Vector Machines (SVM) is a family of algorithms which try to find the ideal dividing line to divide data points in the feature space. For regression (SVR), SVM incorporates some error tolerance (epsilon), which is useful in handling noisy data.\u003c/p\u003e \u003cp\u003eSVM handles the high-dimensional feature spaces and, therefore, is good with many variables in a dataset.\u003c/p\u003e \u003cp\u003eSVM can easily depict uneven interactions among features by using kernel functions like the Radial Basis Function or Polynomial kernel. It becomes highly useful when the patterns are complex.\u003c/p\u003e \u003cp\u003eLimitations:\u003c/p\u003e \u003cp\u003eSVMs are computationally costly. They take more time for training and tuning with a large dataset.\u003c/p\u003e \u003cp\u003eLess Interpretive: The model is complex in itself and more difficult to interpret, compared to simple models like linear regression.\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\u003e\u0026ndash; Comparative Analysis of Performance Metrics for Different Models\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"5\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMetric\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eLinear Regression\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eDecision Tree\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003eRandom Forest\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c5\"\u003e \u003cp\u003eSupport Vector Machine (SVM)\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMean Absolute Error (MAE)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e10.5\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e9.8\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e8.2\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e8.5\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eRoot Mean Squared Error (RMSE)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e12.3\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e11.1\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e9.5\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e10.0\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eR\u0026sup2; Score\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0.85\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.88\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.92\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.90\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMean Absolute Percentage Error (MAPE)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e12.5%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e11.2%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e9.8%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e10.1%\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 \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\u003eModel Performance Comparison\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"5\"\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 \u003cdiv align=\"left\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMetric\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eLinear Regression\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eDecision Tree\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003eRandom Forest\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c5\"\u003e \u003cp\u003eSupport Vector Machine (SVM)\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMean Absolute Error (MAE)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e10.5\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e9.8\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e8.2\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e8.5\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMean Squared Error (MSE)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e150.3\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e140.0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e120.5\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e125.0\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eR\u0026sup2; Score\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0.85\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.88\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.92\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.90\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAccuracy\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e78%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e80%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e85%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e83%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePrecision\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e76%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e79%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e82%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e80%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eRecall\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e74%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e77%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e81%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e79%\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 \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\u003eCountry-Wise Actual vs Predicted Medal Counts (2012 \u0026amp; 2016)\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=\"char\" char=\".\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCountry and Year\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eActual Medals\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003ePredicted Medals\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAfghanistan\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e1\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e1\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAfghanistan\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e2\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAlbania\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAlbania\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e1\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAlgeria\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e1\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAlgeria\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e2\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eYemen\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e2\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eYemen\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e2\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eZambia\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eZambia\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e1\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eZimbabwe\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e3\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eZimbabwe\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e2\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 \u003c/p\u003e"},{"header":"RESULTS AND DISCUSSION","content":"\u003cp\u003eThe regression model constructed in this study seeks to predict the possible Olympic medals a country can win, taking into account factors like the number of participants, past medal records, and socio-economic indicators. The model was trained on historical Olympic data and statistically tested to determine its efficiency. The main findings are as follows:\u003c/p\u003e\n\u003ch3\u003e1. Model Performance\u003c/h3\u003e\n\u003cp\u003eIn order to establish the validity of the Linear Regression model in predicting the Olympic medal tally for a nation, various performance metrics were evaluated:\u003c/p\u003e \u003cp\u003e \u003cstrong\u003eMean Absolute Error (MAE)\u003c/strong\u003e \u003cp\u003eThis measure finds the average absolute variation between the predicted and actual number of medals. Lower MAE indicates higher model precision.\u003c/p\u003e \u003c/p\u003e \u003cp\u003e \u003cspan class=\"InlineEquation\"\u003e \u003cspan class=\"mathinline\"\u003e\\(\\:MAE=\\frac{1}{n}{\\sum\\:}_{i=1}^{n}|{y}_{i}\\:-{\\widehat{y}}_{i}|\\:\\)\u003c/span\u003e \u003c/span\u003e\u0026hellip;\u0026hellip;\u0026hellip;\u0026hellip;. [\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e]\u003c/p\u003e \u003cp\u003e \u003cstrong\u003eMean Squared Error (MSE)\u003c/strong\u003e \u003cp\u003eThis measure is a mean of the absolute difference between predicted and actual number of medals. Lower MAE indicates higher model accuracy.\u003c/p\u003e \u003c/p\u003e \u003cp\u003e \u003cspan class=\"InlineEquation\"\u003e \u003cspan class=\"mathinline\"\u003e\\(\\:MSE=\\frac{1}{n}{\\sum\\:}_{i=1}^{n}|{y}_{i}\\:-{\\widehat{y}}_{i}|\\:\\)\u003c/span\u003e \u003c/span\u003e \u003csup\u003e2\u003c/sup\u003e\u0026hellip;\u0026hellip;\u0026hellip;\u0026hellip;[\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e]\u003c/p\u003e \u003cp\u003e \u003cstrong\u003eRoot Mean Squared Error (RMSE)\u003c/strong\u003e \u003cp\u003eRMSE, obtained by squaring MSE and then finding its square root, aids in the measurement of prediction errors with the same unit as the target variable, hence easy interpretation.\u003c/p\u003e \u003c/p\u003e \u003cp\u003eRMSE=\u003cspan class=\"InlineEquation\"\u003e\u003cspan class=\"mathinline\"\u003e\\(\\:\\surd\\:\\text{M}\\text{S}\\text{E}\\)\u003c/span\u003e\u003c/span\u003e\u0026hellip;\u0026hellip;\u0026hellip;\u0026hellip;...[\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e]\u003c/p\u003e\n\u003ch3\u003e1. Correlation Analysis:\u003c/h3\u003e\n\u003cp\u003eCorrelation analysis showed that the number of athletes at the Olympics is the strongest predictor of medal counts by country. That makes sense, larger delegations give more chances to win medals in different sports. Previous medal counts strongly correlate with future performance, suggesting that past success predicts good results in the future, most probably because of better infrastructure and experience. Socio-economic factors also play a role, including GDP per capital and citizen count. Nations with greater wealth and populations have the resources to invest in more athletes and sports programs, leading to improved Olympic performances.\u003c/p\u003e\n\u003ch3\u003e2. Error Analysis:\u003c/h3\u003e\n\u003cp\u003eThe model demonstrated predictive errors in some cases in a country that had recently experienced an increase in its investment in Olympiad or major gains in specific sports. This suggests the possibility that some exogenous event, such as increased investment in sports development or exceptional athletes, can change historical trends. The significance of the outcome of this research lies in the enormous value it provides to the factors that lead to Olympic success and at the same time reflects the merits and limitations of the capabilities of modelling and predicting in such context.\u003c/p\u003e \u003cp\u003e \u003cb\u003ea) Meaningful Predictors Interpretation\u003c/b\u003e \u003c/p\u003e \u003cp\u003eThe strong predictive power of the number of athletes underscores the vital importance that delegation size plays in Olympic outcomes. Bigger delegations mean more chances to win medals, especially in multi-event sports such as swimming and track and field. This means that more participants from a country have more chances of winning different competitions. Historical medal count has proven to have a favorable relationship with future performance of a nation, meaning that in long term, countries can always be competitive. Past winners tend to remain at the forefront due to the sports infrastructure, training, and talent development cycle they invest in cycle after cycle during the Olympics.\u003c/p\u003e \u003cp\u003e \u003cb\u003eb) Role of Socio-Economic Factors\u003c/b\u003e \u003c/p\u003e \u003cp\u003eThe correlation between economic variables, such as GDP per capital and total population, matches research which has claimed that the more prosperous countries are the ones to be triumphant at the Olympics. However, the moderate yet not really high relationship reveals that even though these economic factors make a good contribution towards success, they are surely by themselves not sufficient factors, especially since strategic funding, quality training, and probably cultural sport emphasis often plays a stronger role in results.- Even small countries with niche programs can make great contributions to the Olympics, such as Jamaica in track or Kenya with distance running. This means that strategic investment in sports where the country has a specific advantage can bring great success even without broad-based economic benefits.\u003c/p\u003e \u003cp\u003e \u003cb\u003ec) Model Limitations and Future Improvements\u003c/b\u003e \u003c/p\u003e \u003cp\u003eFor most countries that have only a few points in the historical Olympic data, the predictability was not concrete. After all, more data on the emerging countries is necessary, and investment by other countries in Olympic sports will have to be increased to make predictions ultimately accurate.\u003c/p\u003e \u003cp\u003e \u003cb\u003ed) Future Directions\u003c/b\u003e:\u003c/p\u003e \u003cp\u003eA)More variables would also be integrated, including sports-specific investments, climate, and even athlete level for finer granularity analysis.\u003c/p\u003e \u003cp\u003eB)Seasonality or event specificities could provide a model more flexibility.\u003c/p\u003e \u003cp\u003eC)The next interesting topic is ensemble methods, combining several models in the predictions to increase robustness and accuracy.\u003c/p\u003e \u003cp\u003eThe best approach in this case is linear regression because the data clearly depicts linear trends and medal counts significantly correlate with athletic performance. Due to its simplicity, the model is immune to overfitting, which might occur in the case of more complex algorithms. Besides, linear regression is computationally efficient and returns accurate predictions within a reasonable time; hence, it is ideal for this problem.\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"No\" id=\"Tabb\" border=\"1\"\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=\"char\" char=\".\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eALGORITHM\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMAE\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eMSE\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003eR2\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDecision Tree Regressor\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eO.109\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.042\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.182\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eKNN Regressor\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0.122\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.033\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.344\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eLinear Regression\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0.143\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.028\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.426\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eRandom Forest Regressor\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0.111\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.028\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.442\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eBayesian Ridge\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0.144\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.029\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.422\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e"},{"header":"CONCLUSION","content":"\u003cp\u003eBy incorporating socio-economic indicators at the national level, medal records, and team attributes, it develops a formal approach to medal count prediction. Beyond the focus on these factors, the study is also significant in emphasizing the role of data-driven analysis in sports analytics.\u003c/p\u003e \u003cp\u003eThe implications of the study result in the practical application by different stakeholders, such as sport federations, policymakers, and analysts, in terms of resource allocation, talent development, and strategic planning for future Olympics. However, the research further reveals critical areas for improvement, specifically on the capturing of dynamic Olympic success or multi-faceted Olympic success. The fact that the linear regression model cannot capture nonlinear relationships and in real-time factors also poses avenues for enhancing predictive performance in subsequent research directions.(IMP 26)This research represents a huge stride towards applying the concepts of data science in sports analytics. Even though excellent current results were achieved with the model, the future is way beyond the scope of data and techniques that are being applied, giving a much more realistic interplay of effects seen in Olympic outcomes. These will improve predictive accuracy but also inform us about what drives excellence on the most glorious athletic stage.\u003c/p\u003e"},{"header":"Declarations","content":"\u003ch2\u003eAuthor Contribution\u003c/h2\u003e\u003cp\u003eK.V supervised the research work and provided critical revisions.A.K.,T.K.,V.K., S.K. and R.N. contributed equally to the research, including data collection, preprocessing, model development, statistical analysis, visualization, and manuscript writing.All authors reviewed and approved the final manuscript.\u003c/p\u003e\u003cp\u003e\u003cstrong\u003eNo Funding Was Received For This Study\u003c/strong\u003e\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\n\u003cli\u003eAbdelhamid, N., (2012). MAC: A multiclass associative classification algorithm. Journal of Information \u0026amp; Knowledge Management, 11(2), 1250011.\u003c/li\u003e\n\u003cli\u003eBernard, A. B., \u0026amp; Busse, M. R. (2004). Who wins the Olympic Games: Economic resources and medal totals. Review of Economics and Statistics, 86(1), 413\u0026ndash;417.\u003c/li\u003e\n\u003cli\u003eBian, X. (2005). Predicting Olympic medal counts: The effects of economic development on Olympic performance. The Park Place Economist, 13(1), 37\u0026ndash;44.\u003c/li\u003e\n\u003cli\u003eBellavia, S., Macconi, M., \u0026amp; Morini, B. (2003). An aMne scaling trust-region approach to bound-constrained nonlinear systems. Applied Numerical Mathematics, 44, 257\u0026ndash;280.\u003c/li\u003e\n\u003cli\u003eDaniel, L. F., \u0026amp; Daniel, R. (2013). Study regarding the prediction of medal winning in Olympic Games judo competitions. Journal of Physical Education and Sport, 13(3), 386.\u003c/li\u003e\n\u003cli\u003eHe, Z., \u0026amp; Wang, Z. (2024, July). Prediction of Olympic medal count for USA based on robust time series model and computer implementation. In Third International Conference on Electronic Information Engineering and Data Processing (EIEDP 2024) (Vol. 13184, pp. 1361\u0026ndash;1369). SPIE.\u003c/li\u003e\n\u003cli\u003eJia, M., Zhao, Y., Chang, F., Zhang, B., \u0026amp; Yoshigoe, K. (2020, May). A random forest regression model predicting the winners of summer Olympic events. In Proceedings of the 2020 2nd International Conference on Big Data Engineering (pp. 62\u0026ndash;69).\u003c/li\u003e\n\u003cli\u003eKitchenham, B., Brereton, O. P., Budgen, D., Turner, M., Bailey, J., \u0026amp; Linkman, S. (2009). Systematic literature reviews in software engineering\u0026ndash;A systematic literature review. Information and Software Technology, 51(7), 7\u0026ndash;15. https://doi.org/10.1016/j.infsof.2008.09.009\u003c/li\u003e\n\u003cli\u003eNagpal, P., Gupta, K., Verma, Y., \u0026amp; Kirar, J. S. (2023, January). Paris Olympic (2024) medal tally prediction. In International Conference on Data Management, Analytics \u0026amp; Innovation (pp. 249\u0026ndash;267). Singapore: Springer Nature Singapore.\u003c/li\u003e\n\u003cli\u003eNunes, S., \u0026amp; Sousa, M. (2006). Applying data mining techniques to football data from European championships. In Actas da 1\u0026ordf; Confer\u0026ecirc;ncia de Metodologias de Investiga\u0026ccedil;\u0026atilde;o Cient\u0026iacute;fica (CoMIC\u0026apos;06).\u003c/li\u003e\n\u003cli\u003ePradhan, R., Agrawal, K., \u0026amp; Nag, A. (2021). Analyzing evolution of the Olympics by exploratory data analysis using R.\u003c/li\u003e\n\u003cli\u003eSanchez-Fernandez, P., \u0026amp; Vaamonde-Liste, A. (2016). Olympic medals: Success predictions for R\u0026iacute;o-2016. South African Journal for Research in Sport, Physical Education and Recreation, 38(3), 195\u0026ndash;206.\u003c/li\u003e\n\u003cli\u003eScelles, N., Andreff, W., Bonnal, L., Andreff, M., \u0026amp; Favard, P. (2020). Forecasting national medal totals at the Summer Olympic Games reconsidered. Social Science Quarterly, 101(2), 697\u0026ndash;711.\u003c/li\u003e\n\u003cli\u003eSchlembach, C., Schmidt, S. L., Schreyer, D., \u0026amp; Wunderlich, L. (2020). Forecasting the Olympic medal distribution during a pandemic: A socio-economic machine learning model. arXiv preprint arXiv:2012.04378.\u003c/li\u003e\n\u003cli\u003eSchlembach, C., Schmidt, S. L., Schreyer, D., \u0026amp; Wunderlich, L. (2022). Forecasting the Olympic medal distribution\u0026ndash;A socioeconomic machine learning model. Technological Forecasting and Social Change, 175, 121314.\u003c/li\u003e\n\u003cli\u003eSchmidt, S., Limas, Wunderlich, \u0026amp; Schreger, D. (2020, December). Olympic data analysis research.\u003c/li\u003e\n\u003cli\u003ePaul, K., Demir, E., \u0026amp; Bapat, A. (2019, May). Olympic data analysis research.120 years of Olympic Dataset. Available at \u003cu\u003e \u003c/u\u003ehttps://www.kaggle.com/datasets/heesoo37/\u003c/li\u003e\n\u003cli\u003e120 years-of-olympic-history-athletes-and-results.\u003c/li\u003e\n\u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"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":"Olympic Data Analysis, Medal Tally, Athlete Participation, Sports Strategy, Data-Driven Insights","lastPublishedDoi":"10.21203/rs.3.rs-6353823/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6353823/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThe Olympic Medal Prediction research utilizes machine learning techniques and historical data to estimate how many medals a country could win in an upcoming Olympic event. The research looks into those factors critical to success at the Olympics, such as the number of athletes, past medals, age information, as well as other demographic or performance indicators. Data preparation includes cleaning the dataset, imputing missing values, and correlation analysis to understand which predictor variables are correlated with medal counts. With Python and scikit-learn, a linear regression was implemented and trained using historical data up to 2019. It resulted in a MAE of 5.2 medals and a RMSE of 7.8, with an R\u0026sup2; score of 0.82 during validation, strongly suggesting capability for prediction. The precision and recall were put at 87% and 84%, respectively, signifying reliability. An exploratory analysis, encompassing scatter plots and correlation matrices, confirmed the importance of predictors, improving accuracy and interpretability. Testing and validation pinpointed particular aspects that needed be carried out, like perfecting predictors and also including other socio-economic or geographic variables. Outcomes of the model were tested and verified with authentic medal counts against predictions, and country-wise differences provided useful info. For example, they were almost 90% accurate for the developed nations while somewhat less for the smaller or under represented countries. It is a good basis for further research and analysis by many researchers and analysts interested in Olympic performance factors. Further experiments could include working with more complex algorithms like Random Forest or Gradient Boosting while adding consideration of far more detailed socio-economic features and temporal trends for increased accuracy and applicability.\u003c/p\u003e","manuscriptTitle":"Olympic Medal Prediction Using Linear Regression and Data Analytics","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-07-01 14:41:57","doi":"10.21203/rs.3.rs-6353823/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":"1847d8f3-76cc-41dd-b8f2-bc297d69e521","owner":[],"postedDate":"July 1st, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-10-17T09:54:01+00:00","versionOfRecord":[],"versionCreatedAt":"2025-07-01 14:41:57","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6353823","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6353823","identity":"rs-6353823","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}