Modeling runners’ performance based on e-monitoring of their heart rate indexes

Alina Epanchintseva, Maxim Bakaev


Today's international sport is a competition of fast managerial decisions, high technology and strong investments. Correspondingly, rational selection of capable sportsmen is crucial for optimal allocation of the limited training resources. In our paper, we perform a pilot experimental study with 14 middle-distance runners and propose a model for predicting performance of athletes that is not based on training process-related factors or on previous performance logs. Instead, we rely on heart rate-related indexes that can be relatively easily monitored using today’s e-sensors and mobile devices. In total, we consider 11 factors, but the best model that explains 89% of the variance in performance on the characteristical 1 km distance includes 5 of them (in addition to the demographic factors). Particularly, high pulses at recovery cross and during speed training negatively affect performance, whereas high maximum pulse has significant positive effect. Interestingly, no factors related to the training process, such as the running volume per week, were significant in the model. We believe that our results, even though preliminary, can be of interest to athletes, trainers and sports managers who seek to optimize the training schedules and form balanced national teams.

Full Text:

PDF (Russian)


I.A. Kulikov, “Planning of training in sport running”, Proceedings of International Conference on Research-intensive technologies and innovations, Belgorod, 2016, pp. 198-202. (in Russian)

S. Lotfi, “Machine Learning for sport results prediction using algorithms”, International Journal of Information Technology and Applied Sciences, 3(3), pp. 148-155, 2021.

D. Prasetio, “Predicting football match results with logistic regression”, IEEE International Conference On Advanced Informatics: Concepts, Theory And Application (ICAICTA), pp. 1-5, 2016.

T. Horvat, J. Job, “The use of machine learning in sport outcome prediction: A review”, Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 10(5), e1380, 2020.

D. Rudrapal et al., A deep learning approach to predict football match result. In Computational Intelligence in Data Mining, Singapore: Springer, 2020, pp. 93-99.

M. Bakaev, T. Avdeenko, “Intelligent information system to support decision-making based on unstructured web data”, ICIC Express Letters 9(4), pp. 1017-1023, 2015.

C. Feely et al., “Providing explainable race-time predictions and training plan recommendations to marathon runners”, Proceedings 14th ACM Conference on Recommender Systems, 2020, pp. 539-544.

W. Waleriańczyk, M. Stolarski, “Personality and sport performance: The role of perfectionism, Big Five traits, and anticipated performance in predicting the results of distance running competitions”, Personality and Individual Differences, vol. 169, 109993, 2021.

Q. Liu et al., “Classification of runners’ performance levels with concurrent prediction of biomechanical parameters using data from inertial measurement units”, Journal of Biomechanics, vol. 112, 110072, 2020.

J.A. Albert et al., “Using Machine Learning to Predict Perceived Exertion During Resistance Training With Wearable Heart Rate and Movement Sensors”, IEEE International Conference on Bioinformatics and Biomedicine (BIBM), 2021, pp. 801-808.

A. Epanchintseva, M. Bakaev, “Predicting Performance and Functional Reserves of Athletes Based on Their Pulse Indicators in Different Trainings”, Proc. Internet and Modern Society (IMS-2022), St. Petersburg: ITMO University, in publishing.

T.A. Putilina, Z.V. Pasechnik. “Methodological particulars of training students in medium distances running”, Proceedings All-Russian Conference on Physical Education and Sport, 2017, pp. 84-87. (in Russian)


  • There are currently no refbacks.

Abava  Absolutech Convergent 2022

ISSN: 2307-8162