This project aims to predict the winner of a cricket match using machine learning techniques. The idea and dataset are sourced from an Unstop challenge, which you can find here.
The project utilizes five different datasets:
- Train Dataset: Used to train the model.
- Test Dataset: Used to evaluate the model's performance.
- Match Data: Provides detailed information about each match.
- Batsman Data: Contains performance statistics for individual batsmen.
- Bowler Data: Contains performance statistics for individual bowlers.
The train and test datasets are the primary datasets here and the rest are additional datasets which are used to create extra features, enhancing the model's accuracy in predicting match outcomes.
The project employs a Gradient Boosting Machine (GBM) classifier to predict the outcome of cricket matches. The GBM classifier is chosen for its effectiveness in handling complex datasets and providing accurate predictions.