An analytics staff needs to provide some recommendations of players currently playing outside of the NBA for the GM to target. Therefore, the purpose of this project is to develop a framework which is capable of predicting players’ performance in the NBA on the basis of their performance in the 4 main European leagues, including EuroLeague, EuroCup, Spain's Liga ACB and Italy's Liga A. This project is composed of four parts as follows:
- Data preprocessing
- Model building (multiple linear regression, random forest, and XGBoost) and parameter tuning (cross validation and grid search)
- Model evaluation (MSE and boxplot)
- Rank aggregation (cross-entropy Monte Carlo algorithm)