Location-Aware Shopping Assistance: Evaluation of a Decision-Theoretic Approach

We have implemented and tested a PDA-based system that gives a shopper directions through a shopping mall on the basis of (a) the types of products that the shopper has expressed an interest in, (b) the shopper's current location, and (c) the purchases that the shopper has made so far. The system uses decision-theoretic planning to compute a policy that optimizes the expected utility of a shopper's walk through the shopping mall, taking into account uncertainty about (a) whether the shopper will actually find a suitable product in a given location and (b) the time required for each purchase. To assess the acceptability of this approach to potential users, on two floors of a building we constructed a mockup of a shopping mall with 15 stores. Each of 20 subjects in our study shopped twice in the mall, once using our system and once using a paper map. The subjects completed their tasks significantly more effectively using thePDA-based shopping guide, and they showed a clear preference for it. They also yielded numerous specific ideas about the conditions under which the guide will be useful and about ways of increasing its usability.