This is the new github link. Now in python and with a webapp.
The model is two parts:
- Basic ML to predict distributions of "points above replacement" for each player
- Optimizations that takes in the prediction distribution, who's been picked, and who's likely to be on the board by your next pick, to optimize for the relative value of picking a player now vs waiting for your very specific team in your league with very specific rules.
Visit fantasyfootballmodels.com
The website was built primarily through ChatGPT as I don't know webdev - so this is all an experiment. If it works, yay! If not, we'll learn. You gotta be arena maxxing.
To run this project locally, follow these steps:
- Clone the repository:
git clone https://github.com/your_username/fantasy-football-models.git
- Navigate to the project directory:
cd fantasy-football-models
- Install dependencies:
pip install -r requirements.txt
- Set up environment variables:
export SECRET_KEY=your_secret_key_here
- Run the application:
flask run
If you'd like to contribute, please fork the repository and make changes as you'd like. Pull requests are warmly welcome.
This project is licensed under the MIT License - see the LICENSE.md file for details.
For more information, contact Jack Soslow on Twitter