AUTHOR(S): Amritashish Bagchi, Nirmal Salvi and Shiny Raizada

ABSTRACT:
The aim of this study was to develop a prediction model to predict the outcome of FIFA World Cup matches. It may help the team captain, coaches or managers to change the tactics accordingly for the second half of the match and it will also help coaches to prepare practice sessions according to this specificity and to be ready to control these variables in competition. The data was collected from 2018 FIFA World Cup. A total 63 match data were recorded, out of which 12 matches were draw and therefore not included in the study. The dependent variable selected for this study was Match Outcome (Win/Loss). Total Shots Taken, Shots On-Target, Shots Blocked, Fouls, Corner Kick, Attempts from Free Kick, Penalty Kick, Penalty Converted, Offside, Ball Possession, Actual Playing Time and Half Time Score were selected as the predictor variables. For the purpose of this study only the first half data was used and in statistical technique Binary Logistic regression was used to predict the outcome of a match (Win/Loss). The result indicates that the developed Logistic regression Model was significant. According to the statistical significance of the predictor variables, they were numerically weighted and can be used to predict the match outcome. The predictor variables such as half time score, attempts from free kick and shots taken were included in the prediction model with coefficient of determination (R2 ) of.223 (Cox & Snell) and .297 (Nagelkerke). The classification matrix shows that 69.6% of match results were correctly classified by the model.

Pages: 339-342  |  989 Views  116 Downloads