Artificial neural networks for predicting the racing time of cross-country skiers from survey-based data

Abstract

This paper proposes for the first time in literature to use machine learning methods and survey-based data for predicting the racing times of cross-country skiers. Particularly, three popular types of artificial neural networks (ANN) including Multilayer Feed-Forward Artificial Neural Network (MFANN), General Regression Neural Network (GRNN) and Radial Basis Function Neural Network (RBFNN) have been used for model development. The utilized dataset is made up of samples related to 370 cross-country skiers with heterogeneous properties, and includes physiological variables such as gender, age, height, weight and body mass index (BMI) along with a rich set of survey-based data. The results reveal that in general, the three ANN-based methods show comparable performance, and can be categorized as feasible tools to predict the racing time of cross-country skiers with acceptable error rates. Furthermore, significant advantages such as the non-exercise-based usage and the applicability to a broader range of cross-country skiers make the prediction models proposed in this study easy-to-use and more valuable.