Resumen
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.