The Wasabi Personal Shopper: a case-based recommender system

Abstract

The Wasabi Personal Shopper (WPS) is a domain-independent database browsing tool designed for on-line information access, particularly for electronic product catalogs. Typically, web-based catalogs rely either on text search or query formulation. WPS introduces an alternative form of access via preference-based navigation. WPS is based on a line of academic research called FindMe systems. These systems were built in a variety of different languages and used custom-built ad-hoc databases. WPS is written in C++, and designed to be a commercial-grade software product, compatible with any SQL-accessible catalog. The paper describes the WPS and discusses some of the development issues involved in re-engineering our AI research system as a general-purpose commercial application.