Skip to content

This project aims to predict FIFA video game player overall ratings using real-life football data. It leverages various machine learning algorithms to establish a correlation between in-game ratings and actual football performance metrics.

Notifications You must be signed in to change notification settings

m1u1s1/Fifa-Overall-Prediction

Repository files navigation

Fifa-Overall-Prediction

This project aims to predict FIFA video game player overall ratings using real-life football data. It leverages various machine learning algorithms to establish a correlation between in-game ratings and actual football performance metrics.

Data The dataset, fifa.csv, contains player attributes including position, age, height, league rank, market value, team FIFA points, playing minutes, assists, goals, yellow cards, win ratio, and more.

Libraries Used Pandas for data handling. Scikit-learn for machine learning model implementation. XGBoost for advanced modeling. Matplotlib and Seaborn for data visualization. Models Linear Regression Ridge Regression Random Forest Regressor XGBoost Regressor Features Player position, age, height, etc. Team performance indicators. Individual player statistics (goals, assists, minutes played, etc.). Objective To accurately predict FIFA overall ratings based on measurable on-field performance.

About

This project aims to predict FIFA video game player overall ratings using real-life football data. It leverages various machine learning algorithms to establish a correlation between in-game ratings and actual football performance metrics.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published