Drift Detection for Identifying Training Patterns Prior to Performance Improvement in Runners
Abstract
The growing popularity of running in Brazil has led to an increase in amateur runner participation, creating a demand for personalized recommendations to support these athletes. This study aimed to identify runners who showed performance improvements by detecting concept drift in their training performance time series. Training metrics were computed and compared between periods preceding performance improvements and declines. It was observed that, in cases of improvement, these metrics were higher compared to the periods preceding performance declines. These differences were statistically significant (p-value < 0.05), indicating which training patterns are associated with performance progression and representing a first step toward deeper insights.
Keywords:
Drift Detection, Running Performance, Time Series Analysis, Sport Analytics
References
Agrahari, S. and Singh, A. K. (2024). Comparison based analysis of window approach for concept drift detection and adaptation. Applied Intelligence, 55(1).
Berndsen, J., Smyth, B., and Lawlor, A. (2019). Pace my race: recommendations for marathon running. In Proceedings of the 13th ACM Conference on Recommender Systems, page 246–250, NY, USA. Association for Computing Machinery.
Besomi, M., Leppe, J., Di Silvestre, M. C., and Setchell, J. (2018). Serun study: Development of running profiles using a mixed methods analysis. PLOS ONE, 13(7):1–18.
Casado, A., Hanley, B., Jiménez-Reyes, P., and Renfree, A. (2021). Pacing profiles and tactical behaviors of elite runners. Journal of Sport and Health Science, 10(5):537 – 549.
Chang, P., Wang, C., Chen, Y., Wang, G., and Lu, A. (2023). Identification of runner fatigue stages based on inertial sensors and deep learning. Frontiers in Bioengineering and Biotechnology, 11.
Knechtle, B., Knechtle, P., Barandun, U., Rosemann, T., and Lepers, R. (2011). Predictor variables for half marathon race time in recreational female runners. Clinics, 66(2):287–291.
Komitova, R., Raabe, D., Rein, R., and Memmert, D. (2022). Time Series Data Mining for Sport Data: a Review. IJCSS, 21(2):17 – 31.
Nakayama, Y., Kudo, K., and Ohtsuki, T. (2010). Variability and fluctuation in running gait cycle of trained runners and non-runners. Gait posture, 31:331–5.
Ogasawara, E. S., Salles, R., Porto, F., and Pacitti, E. (2025). Event Detection in Time Series. Synthesis Lectures on Data Management (SLDM). Springer.
Reusser, M., Sousa, C., Villiger, E., Alvero Cruz, J. R., Hill, L., Rosemann, T., Nikolaidis, P., and Knechtle, B. (2021). Increased participation and decreased performance in recreational master athletes in “berlin marathon” 1974–2019. Frontiers in Physiology, 12:631237.
Smyth, B. (2019). Recommender systems: A healthy obsession. Proceedings of the AAAI Conference on Artificial Intelligence, 33(01):9790–9794.
Stival, M., Bernardi, M., and Dellaportas, P. (2023). Doubly-online changepoint detection for monitoring health status during sports activities. The Annals of App. Statistics, 17.
Suwankan, S., Suwankan, S., Theanthong, A., and Kemarat, S. (2024). Prediction of 10 km running time by physical and training characteristics in recreational runners.
Tanda, G. (2011). Prediction of marathon performance time on the basis of training indices. Journal of Human Sport and Exercise, 6(3):511 – 520.
Thuany, M., Gomes, T. N., and Almeida, M. (2020). Is there any difference between "amateur" and "recreational" runners? a latent class analysis. Motriz. Revista de Educação Física.
Thuany, M., Gomes, T. N., Estevam, L., and Almeida, M. (2021). Crescimento no número de corridas de rua e perfil dos participantes no Brasil.
Tito, N., Paixão, B., Tavares, L., Ogasawara, E., and Amorim, G. (2024). Diferenciando perfis de corredores por meio de pontos de mudança nos treinos. In Anais do XXXIX Simpósio Brasileiro de Bancos de Dados, pages 834–840, Porto Alegre, Brasil. SBC.
Webb, G., Hyde, R., Cao, H., Nguyen, H.-L., and Petitjean, F. (2016). Characterizing concept drift. Data Mining and Knowledge Discovery, 30.
Yung, K. K., Teune, B., Ardern, C. L., Serpiello, F. R., and Robertson, S. (2024). A change-point method to detect meaningful change in return-to-sport progression in athletes. International Journal of Sports Physiology and Performance, 19(9):943 – 948.
Berndsen, J., Smyth, B., and Lawlor, A. (2019). Pace my race: recommendations for marathon running. In Proceedings of the 13th ACM Conference on Recommender Systems, page 246–250, NY, USA. Association for Computing Machinery.
Besomi, M., Leppe, J., Di Silvestre, M. C., and Setchell, J. (2018). Serun study: Development of running profiles using a mixed methods analysis. PLOS ONE, 13(7):1–18.
Casado, A., Hanley, B., Jiménez-Reyes, P., and Renfree, A. (2021). Pacing profiles and tactical behaviors of elite runners. Journal of Sport and Health Science, 10(5):537 – 549.
Chang, P., Wang, C., Chen, Y., Wang, G., and Lu, A. (2023). Identification of runner fatigue stages based on inertial sensors and deep learning. Frontiers in Bioengineering and Biotechnology, 11.
Knechtle, B., Knechtle, P., Barandun, U., Rosemann, T., and Lepers, R. (2011). Predictor variables for half marathon race time in recreational female runners. Clinics, 66(2):287–291.
Komitova, R., Raabe, D., Rein, R., and Memmert, D. (2022). Time Series Data Mining for Sport Data: a Review. IJCSS, 21(2):17 – 31.
Nakayama, Y., Kudo, K., and Ohtsuki, T. (2010). Variability and fluctuation in running gait cycle of trained runners and non-runners. Gait posture, 31:331–5.
Ogasawara, E. S., Salles, R., Porto, F., and Pacitti, E. (2025). Event Detection in Time Series. Synthesis Lectures on Data Management (SLDM). Springer.
Reusser, M., Sousa, C., Villiger, E., Alvero Cruz, J. R., Hill, L., Rosemann, T., Nikolaidis, P., and Knechtle, B. (2021). Increased participation and decreased performance in recreational master athletes in “berlin marathon” 1974–2019. Frontiers in Physiology, 12:631237.
Smyth, B. (2019). Recommender systems: A healthy obsession. Proceedings of the AAAI Conference on Artificial Intelligence, 33(01):9790–9794.
Stival, M., Bernardi, M., and Dellaportas, P. (2023). Doubly-online changepoint detection for monitoring health status during sports activities. The Annals of App. Statistics, 17.
Suwankan, S., Suwankan, S., Theanthong, A., and Kemarat, S. (2024). Prediction of 10 km running time by physical and training characteristics in recreational runners.
Tanda, G. (2011). Prediction of marathon performance time on the basis of training indices. Journal of Human Sport and Exercise, 6(3):511 – 520.
Thuany, M., Gomes, T. N., and Almeida, M. (2020). Is there any difference between "amateur" and "recreational" runners? a latent class analysis. Motriz. Revista de Educação Física.
Thuany, M., Gomes, T. N., Estevam, L., and Almeida, M. (2021). Crescimento no número de corridas de rua e perfil dos participantes no Brasil.
Tito, N., Paixão, B., Tavares, L., Ogasawara, E., and Amorim, G. (2024). Diferenciando perfis de corredores por meio de pontos de mudança nos treinos. In Anais do XXXIX Simpósio Brasileiro de Bancos de Dados, pages 834–840, Porto Alegre, Brasil. SBC.
Webb, G., Hyde, R., Cao, H., Nguyen, H.-L., and Petitjean, F. (2016). Characterizing concept drift. Data Mining and Knowledge Discovery, 30.
Yung, K. K., Teune, B., Ardern, C. L., Serpiello, F. R., and Robertson, S. (2024). A change-point method to detect meaningful change in return-to-sport progression in athletes. International Journal of Sports Physiology and Performance, 19(9):943 – 948.
Published
2025-09-29
How to Cite
TITO, Nathália; TAVARES, Lucas; AMORIM, Glauco Fiorott.
Drift Detection for Identifying Training Patterns Prior to Performance Improvement in Runners. In: BRAZILIAN SYMPOSIUM ON DATABASES (SBBD), 40. , 2025, Fortaleza/CE.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2025
.
p. 795-801.
ISSN 2763-8979.
DOI: https://doi.org/10.5753/sbbd.2025.247710.
