We will be attempting to determine who will win the NBA Most Valuable Player award using machine learning methods such as SVM/Linear Regression. Our findings will be based on the advanced analystics of past MVP winners, their teams and the advanced analytics of this years players. We will then validate and compare the models and make a final conclusion of the work done
In order to make this project happen, data from both basketball reference and kaggle was needed inorder to create the prediction models for the NBA mvp race.
- Pandas
- Excel
- Python
- MatPlotlib
- PerGame - contains all the per game stats of every nba player from 1977 to 2022
- Standing- contains the NBA record standings for every year since 1977
- Voting- Contains the MVP vote share spreads for each season since 1977
- advanced_stats- Contains the advanced stats of every NBA player since 1977
Simply have anaconda installed on your machine and open the jupter notebook. Alternatively this can be exported it into a google collabs notebooks. You also need to download the xslx/csv files as well and load them into your collab session or into your google drive. This way pandas can actually open the file and run the analytics we ran. All the analytics have already been ran and saved in the notebook for everyone to look at