This thesis aims at developing models that would accurately forecast the Most Valuable Player (MVP) of the National Basketball Association (NBA). R programming language was used in this study to implement different techniques, such as Artificial Neural Networks (ANN), K-Nearest Neighbors (KNN), and Linear Regression Models (LRM). NBA statistics were extracted from all of the past MVP recipients and the top five runner-up MVP candidates from the last ten seasons (2009-2019). The objective is to forecast the Point Total Ratio (PTR) for MVP during the regular season. Seven different underlying models were created and applied to the three techniques in order to produce potential outputs for the 2018-19 season. The best models were then selected and optimized to form the MVP forecasting algorithm, which was validated by predicting the MVP of the 2019-20 season. Ultimately, two underlying models were most robust under the LRM framework, which is considered the champion approach. As a result, two combination models were constructed based on the champion approach and proved to be most efficient. The two finalized combination models then served as the forecasting algorithm used to predict players PTR. Using this algorithm, one of the top players in PTR will win the MVP award for the regular season of the NBA. Hence, this proposed algorithm can be used post All-Star selections to determine the Most Valuable Player.