A neighbor selection method based on network community detection for collaborative filtering

The neighbor selection that determines which users are exploited to estimate a target user's ratings has an important influence on the accuracy of recommendations of collaborative filtering based recommender system. Two kinds of ways for neighbor selection: KNN and cluster-based, are lack of specificity which refers to selecting different appropriate neighbors for different given target users, and thus limit the accuracy of recommendation. Therefore, in this paper, firstly, we propose a method that employs the evolutionary algorithm to optimize neighbors for all target users. Secondly, overcoming the high time complexity of the first one, we present another approach in which community detection algorithm is utilized as a preprocessing, and then the evolution algorithm is employed to optimize the neighborhood size for every community. We present experiments on a standard benchmark data-set, and the results show that the two methods both realize the specificity in neighbor selection, and accordingly lead to a higher accuracy of recommendations. Besides, the second one makes a good compromise between the specificity and time complexity.