—Recommender systems have been used tremendously academically and commercially, recommendations generated by these systems aim to offer relevant interesting items to users. Several approaches have been suggested for providing users with recommendations using their rating history, most of these approaches suffer from new user problem (cold-start) which is the initial lack of items ratings. In this paper we suggest utilizing new user demographic data to provide recommendations instead of using rating history to avoid cold-start problem. We present a framework for evaluating the usage of different demographic attributes, such as age, gender, and occupation, for recommendation generation. Experiments are executed using MovieLens dataset to evaluate the performance of the proposed framework.
—Demographic filtering, information retrieval, personalization, recommender system.
The authors are with the Computer Science Department, FCI, Cairo University, Cairo, Egypt (e-mail: firstname.lastname@example.org, email@example.com).
Cite: Laila Safoury and Akram Salah, "Exploiting User Demographic Attributes for Solving Cold-Start Problem in Recommender System," Lecture Notes on Software Engineering vol. 1, no. 3, pp. 303-307, 2013.