This project aims to predict Fantasy Premier League (FPL) points using machine learning techniques. By analyzing historical player data and various features such as player performance, team fixtures, and player attributes, we can build models that can predict the number of points a player is likely to score in future FPL gameweeks.
In the world of fantasy sports, FPL is one of the most popular games. The objective of this project is to develop a machine learning model that can accurately predict the FPL points for players. This can help FPL managers make informed decisions when selecting players for their teams and planning their strategies.
The data used for this project consists of historical FPL player data, including player statistics, team fixtures, and other relevant information. The dataset is collected from reliable sources and is preprocessed to ensure data quality and consistency.
The model takes into account various features that can influence a player's performance and FPL points. Some of the features used in the model include:
- Player performance in previous gameweeks
- Player attributes such as position, age, and nationality
- Team fixtures and opponent strength
- Injuries and suspensions
- Player popularity and ownership
We explore different machine learning models to predict FPL points. Some of the models we experiment with include:
- Linear Regression
- Random Forest
- Gradient Boosting
- Neural Networks
The models are trained on historical data and evaluated using appropriate metrics to measure their performance.
To evaluate the performance of our models, we use various evaluation metrics such as mean squared error (MSE), root mean squared error (RMSE), and mean absolute error (MAE). We also compare the predictions against the actual FPL points to assess the accuracy of our models.
To use this project, follow these steps:
- Clone the repository:
git clone https://github.com/your-username/FPL-ML-Predictions.git - Install the required dependencies:
pip install -r requirements.txt - Run the main script:
python main.py
Make sure you have the necessary Python environment set up and the required packages installed.
Contributions to this project are welcome. If you have any ideas, suggestions, or bug reports, please open an issue or submit a pull request. We appreciate your contributions!
This project is licensed under the MIT License.