9/9/2010 @ 4:00

9/9/2010

University of Illinois
601 E John Street
Champaign, IL 61820-5711

Location:
165 Everitt Lab

Sponsor:
Department of Statistics

Phone:
3-2167

Description:
ABSTRACT: Benefit segmentation, that is, grouping consumers into different segments based on their product preference, is an essential problem of marketing theory and practice. Modern marketing environments impose some new challenges to traditional segmentation methods. For example, companies are adding more and more features into a single product, while the data we could collect from each consumer is of relatively small size. Although most methods in benefit segmentation assume consumers use every product feature in their decision making, recent research has shown that consumers only consider a subset of features. Further, the heterogeneity among consumers in selecting important product features should be used as an additional index for market segmentation and for new product development. In responding to these challenges, we propose a Bayesian approach for collaborative inference among consumers. The proposed method is a Bayesian approach for multi-task learning problems with structure sparsity, where the structures we consider are stochastic groups and graphs. Connections with existing work on structure sparsity are discussed. And we demonstrate the utility of our method on several simulated data sets and a real case study example on online shopping websites. The talk is based on joint work with Jianfeng Xu (UIUC) and Sunghoon Kim (PSU).