MaP2R: A Personalized Maximum Probability Route Recommendation Method Using GPS Trajectories

  • Ge Cui
  • Xin Wang
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10235)


Personalized travel route recommendation refers to the planning of an optimal travel route between two geographical locations based on the road networks and users’ travel preferences. In this paper, we extract users’ travel behaviours from their historical GPS trajectories and propose a personalized maximum probability route recommendation method called MaP2R. MaP2R utilizes the concepts of appearance behaviour and transition behaviour to describe users’ travel behaviours and applies matrix factorization and Laplace smoothing method to estimate users’ travel behaviour probabilities. When making recommendation, a route with the maximum probability of a user’s travel behaviours is generated based on Markov property and searched through a generated behaviour graph. The experimental results on a real GPS trajectory dataset show that the proposed MaP2R achieves better results for travel route recommendations compared with the existing methods.


GPS trajectories Personalized travel route recommendation Collaborative filtering 



The research is supported by the Natural Sciences and Engineering Research Council of Canada Discovery Grant to Xin Wang and National Natural Science Foundation of China (No. 41271387).


  1. 1.
    Chen, Z., Shen, H.T., Zhou, X.: Discovering popular routes from trajectories. In: 27th IEEE International Conference on Data Engineering, pp. 900–911. IEEE Press (2011)Google Scholar
  2. 2.
    Dai, J., Yang, B., Guo, C., Ding, Z.: Personalized route recommendation using big trajectory data. In: IEEE 31st International Conference on Data Engineering, pp. 543–554. IEEE Press (2015)Google Scholar
  3. 3.
    Delling, D., Wagner, D.: Pareto paths with SHARC. In: Vahrenhold, J. (ed.) SEA 2009. LNCS, vol. 5526, pp. 125–136. Springer, Heidelberg (2009). doi: 10.1007/978-3-642-02011-7_13 CrossRefGoogle Scholar
  4. 4.
    Koren, Y., Bell, R., Volinsky, C.: Matrix factorization techniques for recommender systems. Computer 42, 30–37 (2009)CrossRefGoogle Scholar
  5. 5.
    Letchner, J., Krumm, J., Horvitz, E.: Trip router with individualized preferences (TRIP): incorporating personalization into route planning. In: Proceedings of the 18th AAAI Conference on Innovative Applications of Artificial Intelligence, pp. 1795–1800. AAAI Press, Palo Alto (2006)Google Scholar
  6. 6.
    Newson, P., Krumm, J.: Hidden Markov map matching through noise and sparseness. In: Proceedings of the 17th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems. pp. 336–343. ACM Press, New York (2009)Google Scholar
  7. 7.
    Yang, W., Wang, X., Rahimi, S.M., Luo, J.: Recommending profitable taxi travel routes based on big taxi trajectories data. In: Cao, T., Lim, E.-P., Zhou, Z.-H., Ho, T.-B., Cheung, D., Motoda, H. (eds.) PAKDD 2015. LNCS (LNAI), vol. 9078, pp. 370–382. Springer, Cham (2015). doi: 10.1007/978-3-319-18032-8_29 CrossRefGoogle Scholar
  8. 8.
    Zheng, V.W., Cao, B., Zheng, Y., Xie, X., Yang, Q.: Collaborative filtering meets mobile recommendation: a user-centered approach. In: Proceedings of the 24th AAAI Conference on Artificial Intelligence, pp. 236–241. AAAI Press, Palo Alto (2010)Google Scholar
  9. 9.
    Zheng, Y., Xie, X.: Learning travel recommendations from user-generated GPS traces. ACM Trans. Intell. Syst. Technol. (TIST) 2, 1–29 (2011)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  1. 1.Department of Geomatics EngineeringUniversity of CalgaryCalgaryCanada

Personalised recommendations