LIFESTYLE FINDER: Intelligent User Profiling Using Large-Scale Demographic Data

Bruce Krulwich

Abstract


A number of approaches have been advanced for taking data about a user's likes and dislikes and generating a general profile of the user. These profiles can be used to retrieve documents matching user interests; recommend music, movies, or other similar products; or carry out other tasks in a specialized fashion. This article presents a fundamentally new method for generating user profiles that takes advantage of a large-scale database of demographic data. These data are used to generalize user-specified data along the patterns common across the population, including areas not represented in the user's original data. I describe the method in detail and present its implementation in the LIFESTYLE FINDER agent, an internet-based experiment testing our approach on more than 20,006 users worldwide.

Full Text:

PDF


DOI: http://dx.doi.org/10.1609/aimag.v18i2.1292

Copyright © 2014, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.