Collaborating Authors

Hybrid Recommender Systems for Electronic Commerce

AAAI Conferences

System: verifies that it is OK to use the CFRSS. However, after calculating the predicted ratings on items, it finds that none of the items are "good items" (ref.

Knowledge-based Interactive Selling of Financial Services with FSAdvisor

AAAI Conferences

In this paper we describe the knowledge-based recommender application FSAdvisor (Financial Services Advisor) which assists sales representatives in determining personalized financial service portfolios for their customers. Commercially introduced in 2003, FSAdvisor is licensed to a number of major financial service providers in Austria. It supports the dialog between a sales representative and a customer by guaranteeing the consistency and appropriateness of proposed solutions, identifying additional selling opportunities and by providing intelligent explanations for solutions. In the financial services domain (especially in the retail sector) sales representatives can differ greatly in their expertise and level of knowledge. Therefore financial service providers ask for tools effectively supporting sales representatives in the dialog with the customer. Knowledge-based recommender approaches meet these requirements by allowing an intuitive and flexible mapping of marketing and sales knowledge to the representation of a recommender knowledge base. In FSAdvisor we integrate model-based diagnosis, constraint satisfaction and personalization thus supporting customer-oriented sales dialogs. A graphical development environment enables the implementation of financial service knowledge bases for non-programmers which leads to significant reductions of development and maintenance costs.

Semantic ratings and heuristic similarity for collaborative filtering

AAAI Conferences

Collaborative filtering (CF) is a technique for recommending items to a user's attention based on similarities between the past behavior of the user and that of other users. A canonical example is the GroupLens system that recommends news articles based on similarities between users' reading behavior (Resnick, et al. 1994). This technique has been applied to many areas from consumer products to web pages (Resnick Varian, 1997; Kautz, 1998), and has become standard marketing technique in electronic commerce. The input to a CF system is a triple consisting of a user, an object that the user has an opinion about, and a rating that captures that opinion: u, o, r(u,o) . As ratings for a given user are accumulated, it becomes possible to correlate users on the basis of similar ratings and make predictions about unrated items on the basis of historical similarity.

The VITA Financial Services Sales Support Environment

AAAI Conferences

Knowledge-based recommender technologies support customers and sales representatives in the identification of appropriate products and services. These technologies are especially useful for complex and high involvement products such as cars, computers, or financial services. In this paper we present the VITA (Virtualis Tanacsado) financial services recommendation environment which has been deployed for the Fundamenta building and loan association in Hungary. On the basis of knowledge-based recommender technologies, VITA supports sales dialogs between Fundamenta sales representatives and customers interested in financial services (e.g., loans). VITA has been developed and is maintained on the basis of an environment which supports automated testing and debugging of knowledge bases and recommender process definitions. Besides presenting the VITA environment we focus on reporting empirical results which clearly show the payoffs of the deployed application in terms of time savings in the conduction of sales dialogs.

Putting Recommender Systems to Work for Organizations

AAAI Conferences

What recommender systems have in common is an emphasis on leveraging social processes for the purpose of improving information access. Typically, most of the current breed of recommender systems are Internet services with a twofold purpose: providing tailored recommendations and building communities. The issue we focus on here is how to make recommender systems work in organizations and for organizations. Moving from the Internet to Intranets requires shifting the primary focus from sharing recommendations to sharing knowledge and from community-building to community support. Moving recommender systems from the Internet onto Intranets also means turning "leisure-ware" into groupware, creating both new challenges and new opportunities.