Neural Network System for Predicting the Italian Football Lega "Serie A" Season Results

Abstract

The article describes the development of neural network system for predicting the Italian football Lega Serie A season results. To select the initial set, thematic sites containing complete statistics on the necessary characteristics were used. The system based on cost characteristics has 12 input parameters. The average testing error of this system was 3 %. The system allows to evaluate the performance of a football team in a season within the ranking from 1 to 5 positions, where 1 is 1–4 places and entry into the Champions League, and 5 is the team leaving the league. The significance of the input parameters is revealed. The influence of input parameters on the result is also shown.