Designing a Predictive Model Using Artificial Intelligence to Evaluate Training Load in Football Players

Ali Hussein  Ali; Azhaar  A. Shalal

doi:10.47134/jpo.v3i1.2115

Authors

Ali Hussein Ali University of Al-Shatrah
Azhaar A. Shalal University of Al-Shatrah

DOI:

https://doi.org/10.47134/jpo.v3i1.2115

Keywords:

Artificial Intelligence, Predictive Model, Training Load, Football Players, Sports Performance Evaluation

Abstract

The objective of this research is the development of a predictive model using artificial intelligence techniques that makes it possible to evaluate the training load presented by soccer players, with the intention to optimize training programs and ensuring that they are in line with players' capabilities and physiological and physical needs. The model was built using a diverse set of sports and physiological data observed by modern tools utilising high-end technological capabilities. This study centred around designing algorithms that are able to learn from past and present data to predict whether athletes will respond in certain ways to prescribed training loads, therefore supporting more precise and efficient coaching decisions. In addition to supporting the previously studied approaches based on conventional approaches, the proposed model has been shown by us to be more easily adaptable and accurate in evaluation, with a much higher degree of flexibility, enabling it quickly to handle and analyze large volumes of data reliably. The findings from the analysis indicated a great potential for the best use of artificial intelligence within this domain to improve sports performance and mitigate the likelihood of injuries/unstructured training. The success of the model will mainly rely on data quality, which in this case focused on obtaining data from a range of different devices (performance measurement devices, imaging technologies, and biological analysis techniques) to accurately depict each player's physical status [20, 22]. This model helps in delivering the sophisticated analytical tools that enable coaches to continuously monitor training load, and build player-specific training schedule to create a fine balance between load and recovery. ConclusionOverall, this work is among the first steps towards incorporating artificial intelligence into sports development pathways, but also opens up future perspectives that will be characterized by exponential technological progress and will be driven to leverage improvement evaluation and training programme management processes in a more efficient and precise manner.

References

Barry, L., et al. (2022). International Survey of Training Load Monitoring Practices in Competitive Swimming Environments. Journal of Sports Sciences. https://www.sciencedirect.com/science/article/abs/pii/S1466853X21001887ساينس دايركت

Bartels, F., et al. (2024). SoccerGuard: Investigating Injury Risk Factors for Professional Soccer Players with Machine Learning. arXiv Preprint. https://arxiv.org/abs/2411.08901 arXiv

Benson, L. C., et al. (2020). Monitoring workload in team sports with wearable technology. Journal of Orthopaedic & Sports Physical Therapy, 50(11), 605–613. https://www.jospt.org/doi/10.2519/jospt.2020.9753jospt.org DOI: https://doi.org/10.2519/jospt.2020.9753

Bokůvka, D., et al. (2025). Training Load and Fitness Monitoring in Czech Football. Frontiers in Sports Science and Active Living. https://www.frontiersin.org/journals/sports-and-active-living/articles/10.3389/fspor.2025.1513573/fullFrontiers+1Frontiers+1 DOI: https://doi.org/10.3389/fspor.2025.1513573

Branquinho, L., et al. (2025). Training Load in Sport: Current Challenges and Future Perspectives. Frontiers in Sports Science. https://pmc.ncbi.nlm.nih.gov/articles/PMC11885494/PMC+1 DOI: https://doi.org/10.3389/fspor.2025.1574500

Carter, D., & Lee, M. (2018). Collecting and Analyzing Sports Performance Data. Journal of Athletic Monitoring, 22(3), 73-85.

Clarke, K., & Morgan, D. (2021). Enhancing Training Efficiency Using Predictive Models in Football. Journal of Sports Performance, 14(3), 98-107.

Claudino, J. G., et al. (2019). Current Approaches to the Use of Artificial Intelligence for Performance and Injury Risk in Team Sports. Sports Medicine - Open. https://doi.org/10.1186/s40798-019-0202-3 SpringerOpen DOI: https://doi.org/10.1186/s40798-019-0202-3

Collins, R., & Roberts, T. (2022). Artificial Intelligence in Football: New Frontiers for Training and Evaluation. Journal of Sports Technology and Performance, 17(8), 112-124.

Coyne, J. O., et al. (2018). The Current State of Subjective Training Load Monitoring in Sports. Journal of Sports Science and Medicine. https://pmc.ncbi.nlm.nih.gov/articles/PMC6301906/PMC DOI: https://doi.org/10.1186/s40798-018-0172-x

Dudley, C., et al. (2023). Methods of Monitoring Internal and External Loads and Their Implications in Adolescent Athletes. Sports Medicine. https://link.springer.com/article/10.1007/s40279-023-01844-xSpringerLink DOI: https://doi.org/10.1007/s40279-023-01844-x

Feng, Q., et al. (2021). Wearable device-based smart football athlete health prediction algorithm based on recurrent neural networks. Journal of Healthcare Engineering, 2021, 1–10. https://pmc.ncbi.nlm.nih.gov/articles/PMC8349259/PMC DOI: https://doi.org/10.1155/2021/2613300

Gao, Y., et al. (2025). The Role of Artificial Intelligence in Enhancing Sports Performance and Injury Prevention. Frontiers in Public Health. https://doi.org/10.3389/fpubh.2025.1554911 Frontiers DOI: https://doi.org/10.3389/fpubh.2025.1554911

Green, H., & Roberts, F. (2020). Data-Driven Insights for Enhancing Football Performance. International Journal of Sports Data, 30(2), 110-122.

Haller, N., et al. (2024). The Puzzle of Monitoring Training Load in Winter Sports. International Journal of Sports Performance. https://ciss-journal.org/article/view/10017/14124ciss-journal.org DOI: https://doi.org/10.36950/2024.3ciss008

Halson, S. L. (2013). Monitoring Training Load to Understand Fatigue in Athletes. Sports Science Exchange. https://www.gssiweb.org/sports-science-exchange/article/sse-135-monitoring-fatigue-and-recoverygssiweb.org+1PMC+1

Halson, S. L. (2014). Monitoring Training Load to Understand Fatigue in Athletes. Sports Medicine. https://pmc.ncbi.nlm.nih.gov/articles/PMC4213373/PMC+1gssiweb.org+1

Halson, S. L. (2014). Monitoring Training Load to Understand Fatigue in Athletes. Sports Medicine. https://pmc.ncbi.nlm.nih.gov/articles/PMC4213373/ DOI: https://doi.org/10.1007/s40279-014-0253-z

Houtmeyers, K. C., et al. (2021). Load Monitoring Practice in European Elite Football and the Role of Club Beliefs and Resources. Frontiers in Sports Science and Active Living. https://www.frontiersin.org/journals/sports-and-active-living/articles/10.3389/fspor.2021.679824/fullFrontiers+1Frontiers+1 DOI: https://doi.org/10.3389/fspor.2021.679824

Hughes, M., & Franks, I. (1997). Notational Analysis of Sport: Systems for Better Coaching and Performance in Sport. E & FN Spon. https://www.amazon.com/Notational-Analysis-Sport-Performance-Coaching/dp/0419209301en.wikipedia.org

Impellizzeri, F. M. (2022). The 'Training Load' Construct: Why It Is Appropriate and Useful in Sports Science. Journal of Science and Medicine in Sport. https://www.sciencedirect.com/science/article/abs/pii/S1440244021004692ساينس دايركت

Impellizzeri, F. M. (2023). Understanding Training Load as Exposure and Dose. Frontiers in Sports Science. https://pmc.ncbi.nlm.nih.gov/articles/PMC10432367/PMC DOI: https://doi.org/10.1007/s40279-023-01833-0

Jackson, L., & Davis, R. (2021). Predictive Modeling in Sports Training: Methodologies and Applications. Journal of Performance Analytics, 25(1), 12-25.

Johnson, T., & Simmons, P. (2020). The Role of Data Analysis in Sports Evaluation. Journal of Performance Science, 9(4), 25-36.

Liao, H., & Fu, Y. (2025). AI in Football Training: Neural Networks for Player Load Assessment. Scientific Reports. Retrieved from https://www.nature.com/articles/s41598-025-93159-2

Liao, S., & Fu, C. (2025). The optimization of youth football training using deep learning and artificial intelligence. Scientific Reports, 15, 8190. https://www.nature.com/articles/s41598-025-93159-2N DOI: https://doi.org/10.1038/s41598-025-93159-2

Macêdo, A. G., et al. (2024). Load Monitoring Methods for Controlling Training Load in Sports. Applied Sciences. https://www.mdpi.com/2076-3417/14/22/10465MDPI

Macêdo, A. G., et al. (2024). Load Monitoring Methods for Controlling Training Load in Sports. Applied Sciences. https://www.mdpi.com/2076-3417/14/22/10465 DOI: https://doi.org/10.3390/app142210465

Majumdar, A., et al. (2022). Machine learning for understanding and predicting injuries in football players. Sports Medicine - Open, 8, 1–16. https://sportsmedicine-open.springeropen.com/articles/10.1186/s40798-022-00465-4SpringerOpen

Mateus, N., et al. (2024). Empowering the Sports Scientist with Artificial Intelligence in Team Sports Environments. Sensors, 25(1), 139. https://doi.org/10.3390/s25010139 MDPI+1PMC+1 DOI: https://doi.org/10.3390/s25010139

Miller, R., & Wilson, A. (2019). Artificial Intelligence in Sports: Current and Future Applications. Sports Science Review, 18(3), 45-56.

Mitchell, P., & Brown, L. (2021). The Integration of AI and Sports Training in Modern Football. Journal of Emerging Technologies in Sports, 11(3), 53-64.

Murray, A. (2019). Monitoring Training Load in American Football. NSCA Coach. https://www.nsca.com/education/articles/nsca-coach/monitoring-training-load-in-american-football/nsca.com

Musat, C. L., et al. (2024). Diagnostic applications of AI in sports: A comprehensive review. Frontiers in Sports Science, 5, 1–15. https://pmc.ncbi.nlm.nih.gov/articles/PMC11592714/PMC

Patterson, B., & Hughes, L. (2021). Optimizing Training Loads in Football: The Role of Artificial Intelligence. Journal of Sports Physiology, 36(5), 100-112.

Peng, X., et al. (2025). Football Performance Prediction Using Neural Networks and Markov Chain Models. PLOS One. Retrieved from https://journals.plos.org/plosone/article?id=10.1371%2Fjournal.pone.0317604 DOI: https://doi.org/10.1371/journal.pone.0317604

Pietraszewski, P., Terbalyan, A., Roczniok, R., Maszczyk, A., Ornowski, K., Manilewska, D., Kuliś, S., Zając, A., & Gołaś, A. (2025). The Role of Artificial Intelligence in Sports Analytics: A Systematic Review and Meta-Analysis of Performance Trends. Applied Sciences, 15(13), 7254. https://doi.org/10.3390/app15137254 MDPI+1bohrium.com+1 DOI: https://doi.org/10.3390/app15137254

Piłka, T., et al. (2023). Predicting injuries in football based on data collected during training and matches. Sensors, 23(3), 1227. https://www.mdpi.com/1424-8220/23/3/1227MDPI DOI: https://doi.org/10.3390/s23031227

Prys, M., et al. (2023). Integrating Machine Learning for Football Injury Prediction. Journal of Sports Science & Medicine. https://doi.org/10.1016/j.jssm.2023.02.004 ساينس دايركت DOI: https://doi.org/10.1016/j.procs.2023.10.410

Rebelo, A., et al. (2023). From data to action: A scoping review of wearable technologies in sports settings for training adaptation and injury prevention. BMC Sports Science, Medicine and Rehabilitation, 15, 169. https://bmcsportsscimedrehabil.biomedcentral.com/articles/10.1186/s13102-023-00783-4BioMed Central DOI: https://doi.org/10.1186/s13102-023-00783-4

Reis, F. J. J., et al. (2024). Artificial intelligence and machine learning approaches in sports science: Applications in football. Journal of Sports Science & Medicine, 23(1), 1–12. https://pmc.ncbi.nlm.nih.gov/articles/PMC11215955/PMC

Rossi, A., et al. (2017). Effective Injury Forecasting in Soccer with GPS Training Data and Machine Learning. arXiv Preprint. https://arxiv.org/abs/1705.08079 arXiv

Seshadri, D. R., et al. (2019). Wearable sensors for monitoring the internal and external loads of athletes. npj Digital Medicine, 2, 1–11. https://www.nature.com/articles/s41746-019-0149-2Nature DOI: https://doi.org/10.1038/s41746-019-0149-2

Smith, J., & Anderson, T. (2020). Technological Advances in Football Training: Enhancing Competitive Performance. Journal of Sports Technology, 12(4), 89-102.

Staunton, C. A., et al. (2022). Misuse of the term 'load' in sport and exercise science. Journal of Science and Medicine in Sport. https://www.sciencedirect.com/science/article/pii/S1440244021002127ساينس دايركت DOI: https://doi.org/10.1016/j.jsams.2021.08.013

Taylor, R., & Harrison, M. (2019). Integrating AI in Sports Analytics: A Revolutionary Approach to Football. Journal of Football Studies, 21(2), 71-84.

Teixeira, J. E., et al. (2024). Data Mining Paths for Standard Weekly Training Load in Youth Football. Journal of Sports Science & Medicine. https://doi.org/10.1186/s40798-024-00465-4 PMC+1PubMed+1

Teixeira, J. E., et al. (2024). Data Mining Paths for Standard Weekly Training Load in Youth Football. Frontiers in Sports Science. https://pmc.ncbi.nlm.nih.gov/articles/PMC11270353/ DOI: https://doi.org/10.3390/jfmk9030114

Teixeira, T., et al. (2024). Predicting High-Intensity Actions in Football Training Using Machine Learning Models. PLOS One. Retrieved from https://pmc.ncbi.nlm.nih.gov/articles/PMC11270353/

Thomas, G., & Richards, E. (2022). AI and Training Decisions: The Future of Football Coaching. Journal of Sports Coaching, 15(6), 89-101.

Tsilimigkras, D., et al. (2024). Machine Learning Approaches for Football Training Load and Injury Prediction. Journal of Sports Science and Medicine. Retrieved from https://pmc.ncbi.nlm.nih.gov/articles/PMC11366842/

Vicente, H. (2024). The AI Revolution: How Technology is Reshaping Workload Management in Football. HRS Vicente. https://hrsvicente.shorthandstories.com/the-ai-revolution-how-technology-is-reshaping-workload-management-in-football/

Vicente, H. (2024). The AI revolution: How technology is reshaping workload management in football. HRS Vicente. https://hrsvicente.shorthandstories.com/the-ai-revolution-how-technology-is-reshaping-workload-management-in-football/

Wang, C., et al. (2024). Optimization System for Training Efficiency and Load Management in Sports. Journal of Sports Sciences. https://doi.org/10.1016/j.jss.2024.03.012 ساينس دايركت DOI: https://doi.org/10.1016/j.jss.2024.03.012

Wattel, A. (2021). Predicting Training Days in the Short-Term Training Cycle of a Youth Football Team Using Machine Learning. Data Science & Society. https://doi.org/10.3233/JSA-240718 arno.uvt.nl+1journals.sagepub.com+1 DOI: https://doi.org/10.3233/JSA-240718

West, S. (2024). Training-Load Management Ambiguities and Weak Logic. International Journal of Sports Physiology and Performance. https://journals.humankinetics.com/view/journals/ijspp/aop/article-10.1123-ijspp.2024-0158/article-10.1123-ijspp.2024-0158.pdfjournals.humankinetics.com+1

Williams, C., & Lewis, S. (2020). Balancing Training Load and Fatigue: The Role of AI. International Journal of Sports Medicine, 27(1), 45-55.

Williams, S., & Harris, N. (2021). Using AI for Tactical and Physical Training Adjustments in Football. Sports Science Innovations, 18(7), 33-48.