Cross-Domain Recommendation in a Cold-Start Context: The impact of User Profile Size on the Quality of Recommendation

Most of the research studies on recommender systems are\ud focused on single-domain recommendations. With the growth of multi-\ud domain internet stores such as iTunes, Google Play, and Amazon.com,\ud an opportunity to offer recommendations across different domains be-\ud come more and more attractive. But there are few research studies on\ud cross-domain recommender systems. In this paper, we study both the\ud cold-start problem and the hypothesis that cross-domain recommenda-\ud tions provide more accuracy using a large volume of user data from a\ud true multi-domain recommender service. Our results indicate that cross-\ud domain collaborative filtering could significantly improve the quality of\ud recommendation in cold start context and the auxiliary profile size plays\ud an important role in it