HomeOverviewAcademicsResearchPeopleStudent ResourcesSeminars & EventsCareer Center
Operations Research Center
Seminars & Events

Seminars

- Archives

IAP

Events

Skip to content

Fall 2012 Seminar Series

MASSACHUSETTS INSTITUTE OF TECHNOLOGY
OPERATIONS RESEARCH CENTER
FALL 2012 SEMINAR SERIES

DATE: December 11th (rescheduled)
LOCATION: E51-376
TIME: 4:15pm
Reception immediately following

SPEAKER:
Cynthia Rudin

TITLE
Algorithms for Interpretable Machine Learning

ABSTRACT
It is extremely important in many application domains to have transparency in predictive modeling. Domain experts do not tend to prefer "black box" predictive model models. They would like to understand how predictions are made, and possibly, prefer models that emulate the way a human expert might make a decision, with a few important variables, and a clear convincing reason to make a particular prediction.

 

I will discuss recent work, performed in large part by ORC students, on interpretable predictive modeling with decision lists. I will describe several approaches, including:

 

- an algorithm where not only the predictions, but the whole algorithm itself is interpretable to a human

- an algorithm based on Bayesian analysis

- an algorithm based on optimization

 

This talk will feature work by ORC student Ben Letham, ex-ORC student Allison Chang, and ORC co-director Dimitris Bertsimas. It will also feature work by MIT undergraduate Shawn Qian. Other collaborators are David Madigan (Columbia), Tyler McCormick (U. Washington), and Gene Kogan (Independent).


Back to Seminar Series schedule page

MIT home