Training load responses modelling and model generalisation in elite sports

This study aims to provide a transferable methodology in the context of sport performance modelling, with a special focus to the generalisation of models. Data were collected from seven elite Short track speed skaters over a three months training period. In order to account for training load accumulation over sessions, cumulative responses to training were modelled by impulse, serial and bi-exponential responses functions. The variable dose-response (DR) model was compared to elastic net (ENET), principal component regression (PCR) and random forest (RF) models, while using cross-validation within a time-series framework. ENET, PCR and RF models were fitted either individually (Formula: see text) or on the whole group of athletes (Formula: see text). Root mean square error criterion was used to assess performances of models. ENET and PCR models provided a significant greater generalisation ability than the DR model (Formula: see text, Formula: see text, Formula: see text and Formula: see text for Formula: see text, Formula: see text, Formula: see text and Formula: see text, respectively). Only Formula: see text and Formula: see text were significantly more accurate in prediction than DR (Formula: see text and Formula: see text). In conclusion, ENET achieved greater generalisation and predictive accuracy performances. Thus, building and evaluating models within a generalisation enhancing procedure is a prerequisite for any predictive modelling.