An Experimental Evaluation of Machine Learning Models for Basketball Performance Forecasting

Basket Ball performance enhancement is an important area of work which is being currently taken up by the Computing Sciences as an area of research. Various studies are done on using dataset s available from global sources. Deep learning(DL) and Machine learning (ML) models are used exhaustively but still gaps are there in terms of evaluation of datasets and the model most appropriate taking into account the available datasets. As part of an ongoing research experiments are conducted to evaluate performance of different algorithms on available dataset. The important outcome expected from any algorithm is to evaluate the performance of any player based upon certain set of parameters. In the research presented here outcome of certain experiments are presented. Mainly Linear Regression (LR), K-Nearest Neighbor(KNN), Decision Tree Regressor(DTR), Random Forest(RF), XGBoost (XGb)and Support Vector Machine(SVM) models are developed and a comparative assessment of the performance is presented. Through hyperparameter tuning and cross validation performance improvement and reliability is measured. Experimental results show that Linear Regression Algorithm performed best.