Advertisement

MPE: a mobility pattern embedding model for predicting next locations

  • Meng Chen
  • Xiaohui YuEmail author
  • Yang Liu
Article
  • 129 Downloads
Part of the following topical collections:
  1. Special Issue on Social Computing and Big Data Applications

Abstract

The wide spread use of positioning and photographing devices gives rise to a deluge of traffic trajectory data (e.g., vehicle passage records and taxi trajectory data), with each record having at least three attributes: object ID, location ID, and time-stamp. In this paper, we propose a novel mobility pattern embedding model called MPE to shed the light on people’s mobility patterns in traffic trajectory data from multiple aspects, including sequential, personal, and temporal factors. MPE has two salient features: (1) it is capable of casting various types of information (object, location and time) to an integrated low-dimensional latent space; (2) it considers the effect of “phantom transitions” arising from road networks in traffic trajectory data. This embedding model opens the door to a wide range of applications such as next location prediction and visualization. Experimental results on two real-world datasets show that MPE is effective and outperforms the state-of-the-art methods significantly in a variety of tasks.

Keywords

Human mobility patterns Embedding learning Traffic trajectory data Next location prediction 

Notes

Acknowledgments

This work was supported in part by the National Natural Science Foundation of China under Grant No. 61572289, and the NSERC Discovery Grants.

References

  1. 1.
    Chen, M., Liu, Y., Yu, X.: Nlpmm: a next location predictor with markov modeling. In: PAKDD, pp. 186–197. Springer (2014)Google Scholar
  2. 2.
    Chen, M., Yu, X., Liu, Y.: Mining moving patterns for predicting next location. Inf. Syst. 54, 156–168 (2015)CrossRefGoogle Scholar
  3. 3.
    de Brébisson, A., Simon, É., Auvolat, A., Vincent, P., Bengio, Y.: Artificial neural networks applied to taxi destination prediction. arXiv:1508.00021 (2015)
  4. 4.
    Dong, Z., Yu, X., Cui, X., Song, R., Lin, L.: Grandland traffic data processing platform. JCRD, pp. 766–767 (2014)Google Scholar
  5. 5.
    Feng, S., Cong, G., An, B., Chee, Y.M.: Poi2vec: geographical latent representation for predicting future visitors. In: AAAI, pp. 102–108 (2017)Google Scholar
  6. 6.
    Feng, S., Li, X., Zeng, Y., Cong, G., Chee, Y.M., Yuan, Q.: Personalized ranking metric embedding for next new poi recommendation. In: IJCAI, pp. 2069–2075. AAAI Press (2015)Google Scholar
  7. 7.
    Graves, A., Jaitly, N.: Towards end-to-end speech recognition with recurrent neural networks. In: ICML, pp. 1764–1772 (2014)Google Scholar
  8. 8.
    Grover, A., Leskovec, J.: Node2vec: scalable feature learning for networks. In: KDD, pp. 855–864. ACM (2016)Google Scholar
  9. 9.
    Hinton, G., Roweis, S.: Stochastic neighbor embedding. NIPS 41(4), 833–840 (2010)Google Scholar
  10. 10.
    Jia, Y., Wang, Y., Jin, X., Cheng, X.: Location prediction: a temporal-spatial bayesian model. TIST 7(3), 31 (2016)CrossRefGoogle Scholar
  11. 11.
    Jiang, W., Zhu, J., Xu, J., Li, Z., Zhao, P., Zhao, L.: A feature based method for trajectory dataset segmentation and profiling. WWW 20(1), 5–22 (2017)CrossRefGoogle Scholar
  12. 12.
    Le, Q., Mikolov, T.: Distributed representations of sentences and documents. In: ICML, pp. 1188–C1196 (2014)Google Scholar
  13. 13.
    Levy, O., Goldberg, Y.: Neural word embedding as implicit matrix factorization. NIPS 3, 2177–2185 (2014)Google Scholar
  14. 14.
    Lian, D., Zhao, C., Xie, X., Sun, G., Chen, E., Rui, Y.: Geomf: joint geographical modeling and matrix factorization for point-of-interest recommendation. In: KDD, pp. 831–840. ACM (2014)Google Scholar
  15. 15.
    Liu, Q., Wu, S., Wang, L., Tan, T.: Predicting the next location: a recurrent model with spatial and temporal contexts. In: AAAI, pp. 194–200 (2016)Google Scholar
  16. 16.
    Maaten, L., Hinton, G.: Visualizing data using t-sne. JMLR 9(11), 2579–2605 (2008)zbMATHGoogle Scholar
  17. 17.
    Mikolov, T., Sutskever, I., Chen, K., Corrado, G., Dean, J.: Distributed representations of words and phrases and their compositionality. NIPS 26, 3111–3119 (2013)Google Scholar
  18. 18.
    Monreale, A., Pinelli, F., Trasarti, R., Giannotti, F.: Wherenext: a location predictor on trajectory pattern mining. In: KDD, pp. 637–646. ACM (2009)Google Scholar
  19. 19.
    Wang, D., Deng, S., Liu, S., Xu, G.: Improving music recommendation using distributed representation. In: WWW, pp. 125–126. ACM (2016)Google Scholar
  20. 20.
    Xue, A.Y., Zhang, R., Zheng, Y., Xie, X., Huang, J., Xu, Z.: Destination prediction by sub-trajectory synthesis and privacy protection against such prediction. In: ICDE, pp. 254–265. IEEE (2013)Google Scholar
  21. 21.
    Yao, Z., Fu, Y., Liu, B., Liu, Y., Xiong, H.: Poi recommendation: a temporal matching between poi popularity and user regularity. In: ICDM, pp. 549–558. IEEE (2016)Google Scholar
  22. 22.
    Ye, J., Zhu, Z., Cheng, H.: What’s your next move: user activity prediction in location-based social networks. In: SDM, pp. 171–179. SIAM (2013)Google Scholar
  23. 23.
    Yin, H., Cui, B., Huang, Z., Wang, W., Wu, X., Zhou, X.: Joint modeling of users’ interests and mobility patterns for point-of-interest recommendation. In: MM, pp. 819–822. ACM (2015)Google Scholar
  24. 24.
    Yuan, N.J., Zheng, Y., Xie, X., Wang, Y., Zheng, K., Xiong, H.: Discovering urban functional zones using latent activity trajectories. TKDE 27(3), 712–725 (2015)Google Scholar
  25. 25.
    Yuan, Q., Cong, G., Ma, Z., Sun, A., Thalmann, N.M.: Who, where, when and what: discover spatio-temporal topics for twitter users. In: KDD, pp. 605–613 (2013)Google Scholar
  26. 26.
    Yuan, Q., Cong, G., Zhao, K., Ma, Z., Sun, A.: Who, where, when, and what: a nonparametric bayesian approach to context-aware recommendation and search for twitter users. TOIS 33(1), 1–33 (2015)CrossRefGoogle Scholar
  27. 27.
    Zhang, C., Zhang, K., Yuan, Q., Zhang, L., Hanratty, T., Han, J.: Gmove: group-level mobility modeling using geo-tagged social media. In: KDD, pp. 1305–1314. ACM (2016)Google Scholar
  28. 28.
    Zhang, D., Zhao, S., Yang, L.T., Chen, M., Wang, Y., Liu, H.: Nextme: localization using cellular traces in internet of things. TII 11(2), 302–312 (2015)Google Scholar
  29. 29.
    Zhao, S., Zhao, T., King, I., Lyu, M.R.: Geo-Teaser: geo-temporal sequential embedding rank for point-of-interest recommendation. In: WWW, pp. 153–162 (2017)Google Scholar
  30. 30.
    Zhao, S., Zhao, T., Yang, H., Lyu, M.R., King, I.: Stellar: spatial-temporal latent ranking for successive point-of-interest recommendation. In: AAAI, pp. 315–322 (2016)Google Scholar
  31. 31.
    Zheng, K., Zheng, B., Xu, J., Liu, G., Liu, A., Li, Z.: Popularity-aware spatial keyword search on activity trajectories. WWW 20(4), 749–773 (2017)CrossRefGoogle Scholar
  32. 32.
    Zheng, Y.: Trajectory data mining: an overview. TIST 6(3), 29 (2015)CrossRefGoogle Scholar
  33. 33.
    Zhou, J., Tung, A.K., Wu, W., Ng, W.S.: A semi-Lazy?approach to probabilistic path prediction in dynamic environments. In: KDD, pp. 748–756. ACM (2013)Google Scholar
  34. 34.
    Zhou, N., Zhao, W.X., Zhang, X., Wen, J.R., Wang, S.: A general multi-context embedding model for mining human trajectory data. TKDE 28(8), 1945–1958 (2016)Google Scholar
  35. 35.
    Zhu, J., Jiang, W., Liu, A., Liu, G., Zhao, L.: Effective and efficient trajectory outlier detection based on time-dependent popular route. WWW 20(1), 111–134 (2017)CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2018

Authors and Affiliations

  1. 1.School of Information TechnologyYork UniversityTorontoCanada
  2. 2.Physics and Computer Science DepartmentWilfrid Laurier UniversityWaterlooCanada

Personalised recommendations