Moneyball for Football: Identifying Undervalued Players
This project is inspired by the Moneyball philosophy, originally applied in baseball, and seeks to apply similar principles to football. By leveraging statistical analysis, the project aims to identify football players who are undervalued based on their market value compared to their on-field contributions.
Project Goals
Uncover Undervalued Players: Analyze comprehensive player performance metrics to identify players whose market values do not reflect their true on-field contributions.
Data-Driven Decision Making: Utilize statistical models to support decision-making in football management, particularly in player acquisition and team building.
Tools and Technologies
Python: The primary programming language used for data processing and analysis.
Pandas: For data manipulation and handling of large datasets.
Scikit-Learn (sklearn): Machine learning library used for building and evaluating predictive models.
Data Sources
The project utilizes datasets containing comprehensive player performance metrics, which may include:
Player statistics (e.g., goals, assists, tackles, pass completion rate)
Physical attributes (e.g., height, weight, speed)
Market value data
Historical performance trends
Team and league information