Predicting the NBA MVP: Machine Learning Project [part 3 of 3]

This is part 3 of a series where we predict which NBA player will win MVP! You can watch this without having seen parts 1 or 2.

In this video, we'll use machine learning to predict who will win MVP each year. We'll first prepare the data for machine learning and use a Ridge Regression model. We'll then define an error metric, backtest across most of the data set, and iterate on our predictors. We'll end by using a Random Forest model to make predictions.

You'll need to download the data we'll use here - https://github.com/dataquestio/project-walkthroughs/blob/master/mvp/player_mvp_stats.csv .

The code that we write in this video can be found here - https://github.com/dataquestio/project-walkthroughs/blob/master/mvp/machine_learning.ipynb.

If you want to watch parts 1 and 2, you can see them here -

- Part 1 - https://www.youtube.com/watch?v=JGQGd-oa0l4
- Part 2 - https://github.com/dataquestio/project-walkthroughs/blob/master/mvp/player_mvp_stats.csv

Chapters

00:00 Intro
00:55 Looking at the data
01:55 Reading the data into pandas and cleaning it
06:46 Training a machine learning model
16:11 Identifying an error metric
25:55 Implementing backtesting to predict each year
34:59 Diagnosing model performance
37:17 Adding more predictors
42:40 Using a random forest model
45:01 Next steps