This project aims to predict and simulate the outcomes of the FIFA World Cup 2026 matches using historical match data and machine learning techniques. By analyzing various factors such as team rankings, historical performance, and player statistics, the model predicts the probability of each team winning a match. Additionally, it simulates the tournament to forecast the progression of teams through different stages, from the group phase to the finals.
- Predictive Modeling: Utilizes logistic regression to predict match outcomes based on factors like team rankings, total FIFA points, and historical performance.
- Simulation: Simulates the entire FIFA World Cup 2026 tournament to forecast the progression of teams through the group phase, round of 16, quarterfinals, semifinals, and finals.
- Python 3.x
- Libraries: pandas, numpy, matplotlib, seaborn, scikit-learn
- FIFA.ipynb Contains the logistic regression model training code for predicting match outcomes and simulates the FIFA World Cup 2026 tournament and generates predictions for each stage.
- international_matches.csv: Historical match data used for training the model and simulating the tournament.
- Groupes - V3.csv: File containing group stage match fixtures for the FIFA World Cup 2026.
- Incorporate additional features such as player performance metrics and team strategies.
- Integrate a graphical user interface (GUI) for enhanced user interaction.