|
|
xG Statistics in Football Matches: Predictions and Betting
Černý, Sebastian ; Hanus, Luboš (advisor) ; Šťastná, Lenka (referee)
The thesis studies the effectiveness of betting on the results of football matches using Expected Goals (xG) statistics from two sources Understat and FootyS- tats. It evaluates the performance of 6 different models in seasons 2021/2022 and 2022/2023 across the Ąve highest-ranked European leagues using binary logistic regression to predict two possible results, either the home team winning or away team not losing. For betting, several strategies are used based on ex- isting literature. The results are compared to the model containing traditional variables used commonly for predictions in football based on relevant litera- ture. Using both a combination of xG and traditional variables, and only xG variables the results suggest that xG variables are effective for predicting the outcome of football games. The model containing only Understat xG variables yielded 4.18% return on investment (ROI) when betting on every match in both seasons, which was 3.6% more than the model with traditional variables. For betting only on particular matches based on certain criteria, the combined models with both types of variables had the best results, reaching 10.87% ROI that again outperformed the model with traditional variables by approximately 4.5%. JEL ClassiĄcation C10, C53, L83, Z29 Keywords football, expected...
|
guest ::
RSS feed.