MIT Sloan Analytics 2012

Stuart Morgan is attending the 2012 MIT Sloan Analytics Conference.

The good news for all of us in Australia unable to be in Boston is Stuart blogged from the Conference.

The Twitter #tag for the Conference is #SSAC.

In his first post Stuart noted that there were 2000+ delegates in attendance and a very large online community following proceedings. He pointed to the research papers available online.

Stuart’s second post summarised John Guttag‘s presentation that reported the use of Support Vector Machines (SVM) “to predict whether a particular type of pitch will be thrown given with much greater accuracy than the naive model”. Stuart noted that SVMs are “a supervised machine learning technique that have become very popular in a range of computer science domains, which make it possible to detect patterns and classify features of a data set using input factors”. (John Guttag is a co-head of the MIT Computer Science and Artificial Intelligence Laboratory’s Networks and Mobile Systems Group. This group studies issues related to computer networks, applications of networked and mobile systems, and advanced software-based medical instrumentation and decision systems.)

Stuart’s third post from Day 1 summarised a talk by Mark Bashuk on cumulative win/loss probabilities using play by play analyses of NCAA basketball games. Mark described “a method of calculating the probability of a win using a cumulative probabilities with weighted factors for strength of schedule (SOS), home court advantage and temporal segments of the game”. He used data from the 2011 season (1,091,627 plays, collected from 3500 games).

Stuart’s posts from Day 2 of the Conference included reports on:

The full program for the conference is available here. I have really enjoyed Stuart’s perspective on the Conference.

There is a pre-Conference blog with information about speakers. Other bloggers at the Conference included:

Leave a Reply