Abstract

http://ssrn.com/abstract=2428156
 


 



The Automated General Manager: An Unbiased, Backtested Algorithmic System for Drafts, Trades, and Free Agency that Outperforms Human Front Offices


Philip Maymin


NYU Poly - Department of Finance and Risk Engineering

December 12, 2014


Abstract:     
I introduce an automated system and interactive tools for NBA teams to better decide who to draft, who to trade for, and who to sign as free agents. This automated general manager can serve both as an expert-system replacement or complement to a team's front office, and also as a calibrating benchmark to compare against actual team building performance. Backtested over the past ten years, the automated GM outperforms every single team, and by substantial margins that often represent a major portion of the team's market value. From draft decisions alone, the average team lost about $165,000,000 worth of on-court productivity relative to what they could have had with the automated GM. The system is calibrated using an innovative extension of traditional machine learning methods, applied to a uniquely broad historical database that incorporates both quantitative and qualitative evaluations, and offers a variety of performance metrics; it is thus robust, comprehensive, and does not overfit information from the future. I provide virtually all of the interactive tools supporting this paper, including backtesting results, projections, scenario analysis, and more, online, for free, at nbagm(dot)pm.

Number of Pages in PDF File: 8

working papers series





Download This Paper

Date posted: April 24, 2014 ; Last revised: December 13, 2014

Suggested Citation

Maymin, Philip, The Automated General Manager: An Unbiased, Backtested Algorithmic System for Drafts, Trades, and Free Agency that Outperforms Human Front Offices (December 12, 2014). Available at SSRN: http://ssrn.com/abstract=2428156 or http://dx.doi.org/10.2139/ssrn.2428156

Contact Information

Philip Maymin (Contact Author)
NYU Poly - Department of Finance and Risk Engineering ( email )
Brooklyn, NY 11201
United States

Feedback to SSRN


Paper statistics
Abstract Views: 5,448
Downloads: 1,246
Download Rank: 8,182

© 2014 Social Science Electronic Publishing, Inc. All Rights Reserved.  FAQ   Terms of Use   Privacy Policy   Copyright   Contact Us
This page was processed by apollo8 in 0.250 seconds