Implementation of an intelligent product recommender system in an e-store

Authors:
Seyed Ali Bahrainian;Seyed Mohammad Bahrainian;Meytham Salarinasab;Andreas Dengel
Affiliations:
Computer Science Dept., University of Kaiserslautern, Germany;Shahid Beheshti University, Tehran, Iran;Moje Fannavari Houshmand, Iran;Computer Science Dept., University of Kaiserslautern, Germany and Knowledge Management Dept., DFKI, Kaiserslautern, Germany
Venue:
AMT'10 Proceedings of the 6th international conference on Active media technology
Year:
2010

Citing 4
Cited 0

Using collaborative filtering to weave an information tapestry

Communications of the ACM - Special issue on information filtering
Social information filtering: algorithms for automating “word of mouth”

CHI '95 Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
Constructing Web User Profiles: A non-invasive Learning Approach

WEBKDD '99 Revised Papers from the International Workshop on Web Usage Analysis and User Profiling
Carcara: A Multi-agent System for Web Mining Using Adjustable User Profile and Dynamic Grouping

IAT '06 Proceedings of the IEEE/WIC/ACM international conference on Intelligent Agent Technology

Quantified Score

Hi-index	0.00

Visualization

Abstract

With the emergence of new technologies and modern methods of marketing and the increasing intensity of competition among firms and companies for attracting new customers and making them loyal, a novel automatic solution is needed more than ever. The combination of Electronic Customer Relationship Management (E-CRM) and Artificial Intelligence (AI) has appeared as a solution in recent years. Recommending appropriate products to customers according to their needs is one of the methods of CRM. This paper introduces a system named VALA. It is a product recommender system using adjustable customer profiles and a dynamic grouping process which recommends products to each customer dynamically, as his/her preferences change. In other words the User Interface (UI) alters automatically as the customer profile changes. This recommender system combines collaborative filtering and non-collaborative filtering methods in order to come up with useful and unique suggestions for each customer.