This project focuses on building a machine learning system to analyze and predict football player performance using FIFA dataset.
The goal is to estimate three key attributes for each player:
- Attacking ability
- Playmaking skills
- Defensive strength
These predictions are based on a wide range of player features such as physical attributes, technical skills, and mental characteristics.
The project includes several steps:
- Data cleaning and preprocessing
- Feature engineering to create meaningful performance scores
- Encoding categorical variables
- Handling missing values and outliers
- Building and training machine learning and deep learning models
Multiple models were used including:
- Random Forest Regressor
- Gradient Boosting (XGBoost)
- Artificial Neural Networks (ANN)
The models were evaluated using R² Score and Mean Squared Error to measure prediction accuracy.