Predictive Analytics in Sport Management - Applying Machine Learning Models for Talent Identification and Team Performance Forecasting

Aug 4, 2026

The integration of machine learning in sports management transforms decision-making from intuition to data-driven prediction. This study evaluates predictive analytics for talent identification and team performance forecasting in professional basketball using ten seasons of player statistics, physiological measurements, and team outcomes. Random forests, gradient boosting, and neural networks are compared, with an ensemble approach reaching 87.3% accuracy for anticipating future elite players versus 68.5% for traditional scouting. XGBoost yields team outcome prediction with RMSE of 4.12 wins per season and 82.4% variance explained. Feature analysis highlights player efficiency, advanced defensive measures, and injury history as key drivers. Human expert judgment is improved but not replaced, informing recruitment and player development investment with an implementable analytics framework.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages17

Reading Time43 min

AccessFree to download

Introduction

Machine learning and AI in sports analytics

Motivation and stakes in talent identification and performance prediction

Predictive Analytics in Sport Management: Applying Machine Learning Models for Talent Identification and Team Performance Forecasting AyomideAyomikunAjiboye, Muslihat Adejoke Gaffari, Onaara Enitan Obamuwagun Received: 12 August 2025/Accepted 06 October 2025/Published online: 17 October 2025 [https://dx.doi.org/10.4314/cps.v12i7.5](https://dx.doi.org/10.4314/cps.v12i7.5) Abstract: The integration of machine learning in the sphere of sports management is a paradigm shift because there is no longer a need to rely on intuition and make decisions based on data. This study examines the application of predictive analytics to find athletic talent and predict team performance in professional basketball basedon a large set of data on ten seasons of player statistics, physiological measurements, and team performance. A number of machine learning models were used to predict player development and team success including random forests, gradient boosting models, and neural networks. The ensemble method achieved an accuracy rate of 87.3 per cent of anticipating future elite players among draft candidates, and was the first such method todo so much better than the traditional method of scouting, which averaged 68.5 per cent. The XGBoost algorithm performed better in making predictions about the outcomes of teams with an RMSE of 4.12 wins per season and an explanation of 82.4 percent of the variance in team outcomes. Importance of feature analysis revealed that the player efficiency, advanced defense measures and the injury history were the most significant to individual and team performance forecasting. The authors establish that human judgment in talent evaluation by experts can be improved but not substituted by algorithmic evaluation. The insights have significant implications on player development investment, recruitment and competitiveness in an industry that is dominated by data. The research, methodologically, presents an amalgamation framework fusing the statistical accuracy with sport-related understandings, providing organizations with a systematized method of implementing machine learning into their current management frameworks. Keywords: Machine learning, sports management, predictive analytics, talent identification, team performance forecasting, XGBoost Ayomide Ayomikun Ajiboye Department of Mathematical Science, Faculty of Science, Purdue University, Indiana, United States [Email: ](Email: ajiboyeayomide9@gmail.com)[ajiboyeayomide9@gmail.com](Email: ajiboyeayomide9@gmail.com) [Orcid id: 0000-0001-8084-4534](Orcid id: 0000-0001-8084-4534)[ ](Orcid id: 0000-0001-8084-4534)Muslihat Adejoke Gaffari Department of Mathematics and Statistics, East Tennessee State University, Johnson City, Tennessee, USA Email: [adejokecrown@gmail.com](adejokecrown@gmail.com) [Orcid id: 0009-0008-9506-2664](Orcid id: 0009-0008-9506-2664)[ ](Orcid id: 0009-0008-9506-2664)Onaara Enitan Obamuwagun Department ofKinesiology & Sport Management, Texas Tech University, United States of America (USA) Email: [oobamuwagun@gmail.com](oobamuwagun@gmail.com) [1.0 Introduction](1.0 Introduction) Machine Learning (ML) and Artificial Intelligence (AI) are revolutionizing interdisciplinary domains by enabling precise data analysis, predictive modelling, and autonomous functionality (Ademilua, 2021; Adeyemi, 2024) . Their integration fosters innovative approaches for real-time analyticsand automated decision-making across multiple industries (Ufomba & Ndibe, 2023) . Through their capacity to handle extensive datasets, AI and ML continue to advance research and autonomous system performance (Ndibe & Ufomba, 2024) . The broad adoption of these technologies promotes intelligent frameworks that enhance analytical accuracy and operational effectiveness (Ademilua & Areghan, 2022) . By supporting intelligent automation and data-informed reasoning, they provide transformative solutions to contemporary challenges (Dada et al., 2024; Omosunlade, 2

FAQs

What problem does the study address in sports management?

The study targets how to identify athletic talent and forecast team performance using predictive analytics rather than relying on intuition or traditional scouting alone.

Which machine learning models are used for prediction?

The study uses random forests, gradient boosting models, neural networks, and an ensemble method, with XGBoost specifically reported for team outcome prediction.

Which factors most influence talent and team performance forecasting?

Feature analysis indicates that player efficiency, advanced defensive measures, and injury history are the most significant predictors for individual and team performance outcomes.

Aug 4, 2026

Upload by Valentina