Skip to content

Machine Learning Predictor for NBA games that takes into account player stats, team stats.

License

Notifications You must be signed in to change notification settings

ChickenTarm/NBA_Game_Predictor

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

82 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

NBA Game Predictor

Authors

Tarmily Wen and Andrew Petrosky

What is this?

This is a machine learning predictor for NBA games.

Data

We built a scraper to get data from Basketball Reference.

How did we do it?

We tested with a variety of different models, ranging from a simple baseline predictor which just predicts each game based off of the current win percentage of each team to models such as Gaussian Naive Bayes and SVM.

Results

Best test accuracy was 74.3% from SVM so far, compared to 69% from the baseline predictor.

About

Machine Learning Predictor for NBA games that takes into account player stats, team stats.

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages