JSM Preliminary Online Program
This is the preliminary program for the 2009 Joint Statistical Meetings in Washington, DC.

The views expressed here are those of the individual authors
and not necessarily those of the ASA or its board, officers, or staff.

Back to main JSM 2009 Program page

Activity Number: 396
Type: Invited
Date/Time: Wednesday, August 5, 2009 : 8:30 AM to 10:20 AM
Sponsor: Section on Statistics and Marketing
Abstract - #303211
Title: Learning and Harnessing Graphical Models in Online Applications
Author(s): Eric Horvitz*+
Companies: Microsoft Research
Address: , , ,
Keywords: graphical models ; predictive models ; online applications ; behavioral data
Abstract:

We are in an exciting world, marked by the availability of large amounts of behavioral and system data that can be used to build valuable predictive models. I will present background and results on several applications of the use of probabilistic graphical models in online applications. I will first describe the use of case libraries of rich behavioral data to build models that predict the actions and preferences of people who are search and browsing. Then, I will describe the harnessing of predictive models in expected-utility decision making for guiding question answering. Finally, I will discuss the collection of data that includes features representing links and relationships to make inferences about the quality of search results.

  • The address information is for the authors that have a + after their name.
  • Authors who are presenting talks have a * after their name.

Back to the full JSM 2009 program


JSM 2009 For information, contact jsm@amstat.org or phone (888) 231-3473. If you have questions about the Continuing Education program, please contact the Education Department.
Revised September, 2008