Analyzing training performance in sport is usually based on standardized test protocols and needs laboratory equipment, e.g., for measuring blood lactate concentration or other physiological body parameters. Avoiding special equipment and standardized test protocols, we show that it is possible to reach a quality of performance simulation comparable to the results of laboratory studies using training models with nothing but training data. For this purpose, we introduce a fitting concept for a performance model that takes the peculiarities of using training data for the task of performance diagnostics into account. With a specific way of data preprocessing, accuracy of laboratory studies can be achieved for about 50% of the tested subjects, while lower correlation of the other 50% can be explained.

Analyzing training performance in sport is usually based on standardized test protocols and needs laboratory equipment, e.g., for measuring blood lactate concentration or other physiological body parameters. Avoiding special equipment and standardized test protocols, we show that it is possible to reach a quality of performance simulation comparable to the results of laboratory studies using training models with nothing but training data. For this purpose, we introduce a fitting concept for a performance model that takes the peculiarities of using training data for the task of performance diagnostics into account. With a specific way of data preprocessing, accuracy of laboratory studies can be achieved for about 50% of the tested subjects, while lower correlation of the other 50% can be explained.

Training models have been proposed to model the effect of physical strain on fitness. In this work we explore their use not only for analysis but also to generate training plans to achieve a given fitness goal. These plans have to include side constraints such as, e.g., maximal training loads. Therefore plan generation can be treated as a constraint satisfaction problem and thus can be solved by classical CSP solvers. We show that evolutionary algorithms such as differential evolution or CMA-ES produce comparable results while allowing for more flexibility and requiring less computational resources. Due to this flexibility, it is possible to include well known principles of training science during plan generation, resulting in reasonable training plans.