Application of Machine Learning Models for Baseball Outcome Prediction
Source abstract
Abstract
Data science has become an essential component in professional sports, particularly for predicting team performance and outcomes. This study aims to develop and evaluate machine learning models that accurately predict game outcomes in the Chinese Professional Baseball League (CPBL). Method: A total of 859 games from the 2021 to 2023 regular seasons were analyzed, using both traditional baseball statistics and advanced sabermetric indicators such as the Weighted Runs Created Plus (wRC+), Weighted Runs Above Average (wRAA), and Percentage of Leadoff Batters on Base (PLOB%). Five machine learning models—decision tree, logistic regression, Neural Network, Random Forest, and XGBoost—were constructed and assessed through a five-fold cross-validation. Evaluation metrics included accuracy, F1 scores, sensitivity, specificity, and the AUC-ROC. Results: Among the models, logistic regression and XGBoost achieved the highest performance, with an accuracy ranging from 0.89 to 0.93 and an AUC-ROC from 0.97 to 0.98. The feature importance and SHapley Additive exPlanations (SHAP) analysis revealed that the wRC+ and PLOB% were the most influential predictors, reflecting the offensive efficiency and pitching control. Conclusion: The results suggest that combining interpretable machine learning with sabermetrics provides valuable insights for coaches and analysts in professional baseball. Furthermore, incorporating performance weighting based on game context may further enhance model accuracy. This research demonstrates the potential of data-driven strategies in sports analytics and decision-making.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Sports Analytics and Performance
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Physical Education, Fu Jen Catholic University, New Taipei City 24205, Taiwan
Center for Teacher Education, Fu Jen Catholic University, New Taipei City 24205, Taiwan
Physical Education Office, Fu Jen Catholic University, New Taipei City 24205, Taiwan
Department of Sports Performance, National Taiwan University of Sport, Taichung 40401, Taiwan
Graduate Institute of Athletics and Coaching Science, National Taiwan Sport University, Taoyuan 33301, Taiwan
Funding
the Sports Administration, Ministry of Education, Taiwan, under the 2024 Sports Science Project for Competitive Sports
References (39)
Show source-provided references
1. A general perspective of Big Data: Applications, tools, challenges and trends10.1007/s11227-015-1501-1 ↗
2. Neural network modelling for sports performance classification as a complex socio–technical system
3. Big data and tactical analysis in elite soccer: Future challenges and opportunities for sports science10.1186/s40064-016-3108-2 ↗
4. The use of machine learning in sport outcome prediction: A review10.1002/widm.1380 ↗
5. The application of machine learning techniques for predicting match results in team sport: A review10.1613/jair.1.13509 ↗
6. Ouyang, Y., Li, X., Zhou, W., Hong, W., Zheng, W., Qi, F., and Peng, L. (2024). Integration of machine learning XGBoost and SHAP models for NBA game outcome prediction and quantitative analysis methodology. PLoS ONE, 19.10.1371/journal.pone.0307478 ↗
7. Leicht, A.S., Gomez, M.A., and Woods, C.T. (2017). Team performance indicators explain outcome during women’s basketball matches at the Olympic games. Sports, 5.10.3390/sports5040096 ↗
8. Multifactorial analysis of factors influencing elite australian football match outcomes: A machine learning approach10.2478/ijcss-2019-0020 ↗
9. Construction of the Winner Predictive Model in Major League Baseball Games: Use of the Artificial Neural Networks10.5297/ser.1602.004 ↗
10. Cao, C. (2012). Sports Data Mining Technology Used in Basketball Outcome Prediction. [Master’s Thesis, Dublin Institute of Technology]. Available online: https://arrow.tudublin.ie/cgi/viewcontent.cgi?article=1040&context=scschcomdis.
11. Using Artificial Neural Networks to Construct the Winner Prediction Model in Second Grade of Open-Women University Basketball Association of Taiwan
12. Ivanković, Z., Racković, M., Markoski, B., Radosav, D., and Ivković, M. (2010, January 18–20). Analysis of basketball games using neural networks. Proceedings of the 2010 11th International Symposium on Computational Intelligence and Informatics (CINTI), Budapest, Hungary.10.1109/CINTI.2010.5672237 ↗
13. Huang, M.L., and Li, Y.Z. (2021). Use of machine learning and deep learning to predict the outcomes of major league baseball matches. Appl. Sci., 11.10.3390/app11104499 ↗
14. Data Mining to Explore the Key Performance Factors in the National Basketball Association
15. Predicting major league baseball championship winners through data mining10.30958/ajspo.3.4.1 ↗
16. Predicting Win-Loss outcomes in MLB regular season games–A comparative study using data mining methods10.1515/ijcss-2016-0007 ↗
17. Linardatos, P., Papastefanopoulos, V., and Kotsiantis, S. (2020). Explainable ai: A review of machine learning interpretability methods. Entropy, 23.10.3390/e23010018 ↗
18. Samek, W., Wiegand, T., and Müller, K.R. (2017). Explainable artificial intelligence: Understanding, visualizing and interpreting deep learning models. arXiv.
19. Chen, P.-C. (2022). Comparison of RandomForest and XGBoost in Forecasting Robustness. [Ph.D. Thesis, Master’s Program in Applied Statistics, Department of Statistics, Tamkang University].
20. Exploiting sports–betting market using machine learning10.1016/j.ijforecast.2019.01.001 ↗
21. Kahn, J. (2003). Neural Network Prediction of NFL Football Games, IEEE Computer Society. Available online: https://www.researchgate.net/publication/266334198_Neural_Network_Prediction_of_NFL_Football_Games.
22. Predicting NBA games using neural networks
23. Neural network quarterbacking10.1109/45.535226 ↗
24. A comparative analysis of data mining methods in predicting NCAA bowl outcomes10.1016/j.ijforecast.2011.05.002 ↗
25. Predicting the cricket match outcome using crowd opinions on social networks: A comparative study of machine learning method10.22452/mjcs.vol30no1.5 ↗
26. Analyzing basketball games by a support vector machines with Decision Tree model10.1007/s00521-016-2321-9 ↗
27. Wu, J., Li, Y., and Ma, Y. (2021, January 12–14). Comparison of XGBoost and the Neural Network model on the class-balanced datasets. Proceedings of the 2021 IEEE 3rd International Conference on Frontiers Technology of Information and Computer (ICFTIC), Greenville, SC, USA.10.1109/ICFTIC54370.2021.9647373 ↗
28. A hierarchical Bayesianvariable selection approach to Major League Baseball hitting metrics
29. Sanford, G.D. (2018). What Raw Statistics Have the Greatest Effect on wRC+ in Major League Baseball in 2017, University of Minnesota Digital Conservancy. Available online: http://hdl.handle.net/11299/199934.
30. Tripin, J. (2025, April 14). An Idiot’s Guide to Advanced Statistics: wOBA and wRC+. Available online: https://www.lookoutlanding.com/2017/3/7/14783982/an–idiots–guide–to–advanced–statistics–woba–and–wrc–sabermetrics.
31. Kupiec, R. (2020). Can Statcast Variables Explain the Variation in Weighted Runs Created Plus?. [Master’s Thesis, DePauw University].
32. Weinberg, N. (2025, March 28). How to Evaluate a Hitter, Sabermetrically [Internet]. Available online: https://www.beyondtheboxscore.com/2014/5/26/5743956/sabermetrics–stats–offense–learn–sabermetrics.
33. Bradbury, J.C. (2007). The Baseball Economist: The Real Game Exposed, Dutton.
34. Tango, T.M., Lichtman, M.G., and Dolphin, A.E. (2007). The Book: Playing the Percentages in Baseball, Potomac Books, Inc.
35. Chiu, Y.-C. (2022). Machine Learning Applications for Baseball Coaching Decision-Making: Case Study of Utilizing the Batter-Pitcher Matchups and Forecasting the Hitters’ Value. [Ph.D. Thesis, The In-Service Master’s Program in Multimedia Network Communication and Digital Learning, National Ilan University].
36. Detweiler, H. (2025, April 14). Success in Professional Baseball: The Value of Above Average Position Players; 2014. Available online: https://digitalcommons.liberty.edu/cgi/viewcontent.cgi?article=1444&context=honors.
37. The Moderating Effect of Hardiness on the Relationship Between Trait Anxiety and Performance in Collegiate Baseball Players
38. Analysis of Pitchers’ “Expected-Base-Loss” in the Chinese Professional Baseball League using Machine Learning Methods
39. Li, S.F., Huang, M.L., and Li, Y.Z. (2022). Exploring and selecting features to predict the next outcomes of MLB games. Entropy, 24.10.3390/e24020288 ↗