Michael K. Papamichael        

 

 
  
 View page in separate tab or window
  |  
 View page in separate tab or window
  |  
 View page in separate tab or window
  |  
  |  
  |  
  |  
 


NBA Oracle - Applying Machine Learning methods for basketball game outcome prediction and decision support.

Group Members
  • Michael Papamichael
  • Matthew Beckler
  • Hongfei Wang
Project Description
The importance of well-informed decisions regarding player aquisitions and predicting game outcomes in the professional sports business is critical; even moreso in the NBA, which is a multi-billion dollar industry on its own [3]. The goal of this project is to learn, explore, and apply machine learning techniques to an existing dataset of NBA and ABA basketball statistics to: 1) Predict the outcome of a game, given the two participating teams, and 2) Identify outstanding players based on season and career statistics. In addition to our two original goals, after having extensively examined and worked with our data set and having learned about clustering techniques in class, we are now also interested in applying machine learning clustering techniques to infer player positions.

Project Poster - The project poster can be found here. (voted 2nd best poster during the Machine Learning course public poster session)



Project Proposal - The full project proposal can be found here .

Project Midway Report - The project midway report can be found here .