Training load responses modelling and model generalisation in elite sports

Abstract

Abstract 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 ( $$M_{I}$$ M I ) or on the whole group of athletes ( $$M_{G}$$ M G ). 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 ( $$p = 0.018$$ p = 0.018 , $$p < 0.001$$ p < 0.001 , $$p = 0.004$$ p = 0.004 and $$p < 0.001$$ p < 0.001 for $$ENET_{I}$$ E N E T I , $$ENET_{G}$$ E N E T G , $$PCR_{I}$$ P C R I and $$PCR_{G}$$ P C R G , respectively). Only $$ENET_{G}$$ E N E T G and $$RF_{G}$$ R F G were significantly more accurate in prediction than DR ( $$p < 0.001$$ p < 0.001 and $$p < 0.012$$ p < 0.012 ). 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.