Events calendar

11.00 - 12.30 Thursday 11 Apr 2013

On campus - London - United Kingdom

MSO Seminar: Dorothee Honhon

Speaker(s): Dorothee Honhon

MSO Seminar: Dorothee Honhon - Learning consumer tastes through dynamic assortments: parametric and non-parametric approaches

Abstract:
How should a firm modify its product assortment over time when learning about consumer tastes? We study dynamic assortment decisions in a horizontally differentiated product category for which consumers’ diverse tastes can be represented as locations on a Hotelling line. Each period, the firm offers an assortment to maximize expected total profits over a finite horizon given its subjective beliefs on consumer tastes. The consumers choose a product that maximizes their own utility and the firm updates its beliefs on consumer tastes in a Bayesian fashion after having observed the sales of each product in the assortment. We model this problem as a discrete time dynamic program.
First we assume that the firm knows all possible consumer locations, comprising a finite set, but does not know their probability distribution. We study the tradeoff between the immediate profits from sales in the current period (exploitation) and the informational gains to be exploited in all future periods (exploration). Then we develop a nonparametric Bayesian model using Polya tree priors that makes no assumptions on the form of the consumer taste distribution. Our nonparametric learning model results in optimal profits that are robust to misspecification of the form of consumer taste distributions.

Event location

LT5

Contact: Vicki Sale - Email: vsale@london.edu Tel: 8821