ADVISOR SUITE - A knowledge-based sales advisory system
Dietmar Jannach · 2004
In many domains, a large variety of comparable products and services from different manufacturers is available on the market. As a result, customers are increasingly overwhelmed when they have to choose the products that match their personal needs and preferences because the selection process in many cases requires deep technical knowledge about the product features. In the online sales channel, recommender systems have already been successfully applied as an additional means for improved customer guidance. Realworld sales advisory, however, can be a knowledge-intensive task, where the customer preferences and the suitable sets of products have to be determined in an interactive dialogue. In this paper we present ADVISOR SUITE, a now-commercialized system for building such intelligent, personalized sales advisory applications. The system consistently follows a knowledge-based approach where all required development activities - from the definition of the user model and the recommendation rules, up to the personalization of the dialogue flow as well as user interface generation - are based on simple conceptual models and declarative knowledge representation. All these tasks are also supported by a set of graphical tools comprehensible for nonprogrammers, which leads to significant reductions in development and maintenance costs. Experiences from several commercial instantiations of the presented system are discussed in the final sections.