Improving User Profiles for E-Commerce by Genetic Algorithms
Yi-Shin Chen, Cyrus Shahabi · Studies in fuzziness and soft computing · 2002
Recommendation systems are widely adopted in e-commerce businesses for helping customers locate products they would like to purchase. The major challenge for these systems is bridging the gap between the physical characteristics of data with the users’ perceptions. In order to address this challenge, employing user profiles to improve accuracy becomes essential. However, the system performance may degrade due to inaccuracy of user profiles. Therefore, an effective system should offer learning mechanisms to correct erroneous user inputs. In this paper, we extend an existing recommendation system, Yoda, to improve the profiles automatically by utilizing users’ relevance feedback with genetic algorithms (GA). Our experimental results indicate that the retrieval accuracy is significantly increased by using the GA-based learning mechanism.