Route recommendation based on temporal–spatial metric

Abstract The acquisition and analysis of large amounts of mobile trajectory data promote the rapid development of mobile recommender systems, which can essentially recommend a series of positions to the mobile users. In this paper, we concentrate on the mobile sequential recommendation problem by considering both the distance and time factors, the objective of which is to recommend an optimal driving route consisting of a sequence of pick-up locations for the drivers. Firstly, we formulate this problem and develop a potential travel cost function to comprehensively evaluate each candidate route. Then we propose an efficient and effective R oute recommendation based on T emporal- S patial metric scheme called RTS, which adopts the simulated annealing algorithm and can achieve real-time route recommendation without severely sacrificing the recommendation performance. The extensive experiments based on both the real-world and synthetic data are conducted, the results of which demonstrate the efficiency and effectiveness of the proposed RTS scheme.