Embedded Files
Predicting Credit Default: Saving Millions with a 61% Recall RateÂ
Predicting Credit Default: Saving Millions with a 61% Recall RateÂ
Read Case Study (Medium) -> Link to Medium article
View Source Code (GitHub) -> Link to GitHub Repository
In modern football, overpaying in the transfer market can derail a club's financial stability. I extracted and processed complex performance datasets from Transfermarkt to build a predictive valuation tool for data-driven scouting.
- The ML Strategy: Engineered and deployed a robust XGBoost regression model. By analyzing advanced performance metrics and isolating key feature importances, the model strips away speculative hype to accurately calculate a player's baseline market value.
- The Streamlit Deployment: Bridged the gap between data science and end-users by deploying the model via an interactive Streamlit web application. This allows sports directors to dynamically input player statistics and receive real-time, objective financial estimates.
- Business Impact: This automated valuation framework empowers sports management to transition from intuition-based negotiations to strategic, data-backed investments, maximizing ROI and mitigating financial risk during transfer windows.
Page updated
Google Sites
Report abuse