Predicting cross-country results using feature selection and evolutionary computation

Abstract

Although some work has been done to better predict the outcome of sporting events, it has focused on mainstream sports such as football and has typically employed forecasting or machine learning techniques. This work focuses on the sport of cross-country, and uses feature selection and evolutionary computation to better predict National Meet results. Feature Selection is utilized to find the most optimal feature set and a Particle Swarm Optimizer (PSO) to find the most optimal weight set. The best results are attained using the PSO, with an improvement over the current system of 2.5% for Women and 0.3% for Men.