Mobile location-aware personalized recommendation with clustering-based collaborative filtering

Abstract

The high improvement of mobile communication technology and the reduction in cost of hardware have accelerated the wide popularity of mobile application, in which the personalized recommendation is playing a more and more important role in users' preferences and needs. This paper presents a novel approach of location-aware personalized recommendation by clustering-based collaborative filtering, providing recommendation list for users according to their current positions from mobile devices. First, users are partitioned into different clusters by k-means algorithm, in order to speed up the process for searching the nearest neighbors. Second, the location-aware factor is computed according to the user's acceptable distance of items, which is changing over time. Third, the recommendation list is produced by combining location-aware factor with clustering-based collaborative filtering. An application system of hotel recommendation is developed to illustrate and test the feasibility and effectiveness. © 2012 Praise Worthy Prize S.r.l. - All rights reserved.