Rapid Development of Knowledge-Based Conversational Recommender Applications with Advisor Suite

Knowledge-based recommender systems are Web-based applications that exploit deep domain knowledge for generating buying proposals that match the individual needs and requirements of an online user. As in many domains the detailed customer requirements have to be elicited in an interactive dialog before the recommendation can be made, the development and in particular also the maintenance of the dynamic Web pages that form this personalized dialog are critical tasks, mostly because of the typically strong interdependencies between the recommendation and personalization knowledge. In this paper, we present ADVISOR SUITE, an integrated, domain-independent environment for the development of highly-interactive, personalized recommender applications. The main pillars of the presented system are a) an integrated, model-driven approach for designing all the required recommendation-, personalizationand interaction knowledge, and b) a mechanism that allows for the automatic generation of Web applications, which is of particular importance in prototyping-based, evolutionary development approaches. On the basis of the experiences we have made with the system in several industrial projects, we finally summarize key criteria and best practices of how to efficiently develop high-quality recommender applications with ADVISOR SUITE.