Skip to content

NBA players individual performance perdictions using Neural Networks. Comparison between LSTM and Feed Forward Architectures. Created by Meitar Bach, Mai Elenberg and Lior Ben-Ami

Notifications You must be signed in to change notification settings

MeitarBach/nba-individual-predictions-lstm

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 

Repository files navigation

Predicting NBA Players Individual Performance Using LSTM - Fantasy Basketball has never been Easier!

Fantasy Basketball is a simple game, each user plays the role of a general manager and fills out a roster by drafting actual basketball players. The measure of success in the game is based on the players’ performance in real life. As fantasy basketball enphusiasts while playing the game and going through players statistics, the idea of using this data for predicting players' performances in order to construct a winning team at the available budget arose.

In this notebook you'll find a step by step process of building training and experimenting with a LSTM Neural Network, designed to predict NBA Players Efficiency Rating (PER) scores based on previous games data.

We hope you enjoy!

Meitar Bach, Mai Elenberg, Lior Ben-Ami

About

NBA players individual performance perdictions using Neural Networks. Comparison between LSTM and Feed Forward Architectures. Created by Meitar Bach, Mai Elenberg and Lior Ben-Ami

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published