Skip to main content

Advertisement

Springer Nature Link
Log in

A time-aware trajectory embedding model for next-location recommendation

  • Regular Paper
  • Published:
Knowledge and Information Systems Aims and scope Submit manuscript

Abstract

Next-location recommendation is an emerging task with the proliferation of location-based services. It is the task of recommending the next location to visit for a user, given her past check-in records. Although several principled solutions have been proposed for this task, existing studies have not well characterized the temporal factors in the recommendation. From three real-world datasets, our quantitative analysis reveals that temporal factors play an important role in next-location recommendation, including the periodical temporal preference and dynamic personal preference. In this paper, we propose a Time-Aware Trajectory Embedding Model (TA-TEM) to incorporate three kinds of temporal factors in next-location recommendation. Based on distributed representation learning, the proposed TA-TEM jointly models multiple kinds of temporal factors in a unified manner. TA-TEM also enhances the sequential context by using a longer context window. Experiments show that TA-TEM outperforms several competitive baselines.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8

Similar content being viewed by others

Notes

  1. https://foursquare.com/about/.

  2. To check the recall of the ground-truth location using the above candidate generation method, we compute the hit ratios of the ground-truth location among the 5000 nearest locations on the three datasets as follows: 93, 96 and 98%. It can be seen the majority of the ground-truth locations were recalled using 5000 nearest locations.

  3. It was originally proposed for next-basket recommendation in shopping, and we have slightly modified it to adapt to the current two tasks.

  4. https://radimrehurek.com/gensim/index.html.

  5. Due to multi-threading techniques, the time cost does not show a strict linear increase with the increasing of VS.

References

  1. Altman RM (2007) Mixed hidden markov models: an extension of the hidden markov model to the longitudinal data setting. J Am Stat Assoc 102(477):201–210

    Article  MathSciNet  MATH  Google Scholar 

  2. Cheng C, Yang H, Lyu MR, King I (2013) Where you like to go next: successive point-of-interest recommendation. In: Proceedings of the 23rd International Joint Conference on Artificial Intelligence, Beijing, China, 3–9 August 2013, pp 2605–2611

  3. Cheng H, Ye J, Zhu Z (2013) What’s your next move: user activity prediction in location-based social networks. SDM 13:171–179

    Google Scholar 

  4. Feng S, Li X, Zeng Y, Cong G, Chee YM, Yuan Q (2015) Personalized ranking metric embedding for next new POI recommendation. In: Proceedings of the twenty-fourth international joint conference on artificial intelligence, IJCAI 2015, Buenos Aires, Argentina, 25–31 July 2015, pp 2069–2075

  5. Lai S, Liu K, He S, Zhao J (2016) How to generate a good word embedding. IEEE Intell Syst 31(6):5–14

    Article  Google Scholar 

  6. Le QV, Mikolov T (2014) Distributed representations of sentences and documents. In: Proceedings of the 31th international conference on machine learning, ICML 2014, Beijing, China, 21–26 June 2014, pp 1188–1196

  7. Levandoski JJ, Sarwat M, Eldawy A, Mokbel MF (2012) Lars: a location-aware recommender system. In: ICDE ’12, pp 450–461

  8. Li X, Cong G, Li X-L, Pham T-AN, Krishnaswamy S (2015) Rank-geofm: A ranking based geographical factorization method for point of interest recommendation. In: SIGIR’15, pp 433–442

  9. Li Y, Nie J, Zhang Y, Wang B, Yan B, Weng F (2010) Contextual recommendation based on text mining. In: COLING’10, pp 692–700

  10. Lian D, Zhao C, Xie X, Sun G, Chen E, Rui Y (2014) Geomf: joint geographical modeling and matrix factorization for point-of-interest recommendation. In: KDD’14, pp 831–840

  11. Liu B, Fu Y, Yao Z, Xiong H (2013) Learning geographical preferences for point-of-interest recommendation. In: KDD’13, pp 1043–1051

  12. Liu X, Liu Y, Aberer K, Miao C (2013) Personalized point-of-interest recommendation by mining users’ preference transition. In: CIKM ’13, pp 733–738

  13. Mikolov T, Chen K, Corrado GS, Dean J (2013) Efficient estimation of word representations in vector space. In: Proceedings of workshop at ICLR

  14. Mikolov T, Sutskever I, Chen K, Corrado GS, Dean J (2013) Distributed representations of words and phrases and their compositionality. In: NIPS ’13, pp 3111–3119

  15. Mimno D, McCallum A (2007) Expertise modeling for matching papers with reviewers. In: KDD ’07, pp 500–509

  16. Morin F, Bengio Y (2005) Hierarchical probabilistic neural network language model. In: Proceedings of AISTATS, pp 246–252

  17. Noulas A, Scellato S, Lathia N, Mascolo C (2012) A random walk around the city: new venue recommendation in location-based social networks. In: Proceedings of PASSAT, pp 144–153

  18. Rendle S, Freudenthaler C, Schmidt-Thieme L (2010) Factorizing personalized Markov chains for next-basket recommendation. In: WWW ’10, pp 811–820

  19. Usunier N, Buffoni D, Gallinari P (2009) Ranking with ordered weighted pairwise classification. In: ICML ’09, pp 1057–1064

  20. Wang P, Guo J, Lan Y, Xu J, Wan S, Cheng X (2015) Learning hierarchical representation model for nextbasket recommendation. In: SIGIR ’15, pp 403–412

  21. Wu X, Liu Q, Chen E, He L, Lv J, Cao C, Hu G (2013) Personalized next-song recommendation in online karaokes. In: RecSys ’13, pp 137–140

  22. Yang D, Zhang D, Bingqing Q (2016) Participatory cultural mapping based on collective behavior data in location-based social networks. ACM TIST 7(3):30

    Google Scholar 

  23. Ye M, Liu X, Lee W-C (2012) Exploring social influence for recommendation: a generative model approach. In: SIGIR ’12, pp 671–680

  24. Ye M, Yin E, Lee W-C, Lee D-L (2011) Exploiting geographical influence for collaborative point-of-interest recommendation. In: SIGIR ’11, pp 325–334

  25. Yin H, Sun Y, Cui B, Hu Z, Chen L (2013) Lcars: a location-content-aware recommender system. In: KDD ’13, pp 221–229

  26. Yuan Q, Cong G, Ma Z, Sun A, Thalmann NM (2013) Time-aware point-of-interest recommendation. In: SIGIR ’13, pp 363–372

  27. Zhao WX, Jiang J, He J, Shan D, Yan H, Li X (2010) Context modeling for ranking and tagging bursty features in text streams. In: Proceedings of the 19th ACM conference on information and knowledge management, CIKM 2010, Toronto, Ontario, Canada, 26–30 October 2010, pp 1769–1772

  28. Zheng VW, Cao B, Zheng Y, Xie X, Yang Q (2010) Collaborative filtering meets mobile recommendation: a user-centered approach. In: AAAI ’10

  29. Zhou N, Zhao WX, Zhang X, Wen JR, Wang S (2016) A general multi-context embedding model for mining human trajectory data. IEEE Trans Knowl Data Eng 28(8):1945–1958

    Article  Google Scholar 

Download references

Acknowledgements

The authors thank the anonymous reviewers for their valuable and constructive comments. The work was partially supported by National Natural Science Foundation of China under the Grant Number 61502502, Beijing Natural Science Foundation under the Grant Number 4162032, the National Key Basic Research Program (973 Program) of China under Grant No. 2014CB340403, and the open fund with the Grant Number MJUKF201703 from Fujian Provincial Key Laboratory of Information Processing and Intelligent Control (Minjiang University).

Author information

Authors and Affiliations

  1. School of Information, Renmin University of China, Beijing, China

    Wayne Xin Zhao, Ningnan Zhou & Ji-Rong Wen

  2. Beijing Key Laboratory of Big Data Management and Analysis Methods, Beijing, China

    Wayne Xin Zhao & Ji-Rong Wen

  3. Fujian Provincial Key Laboratory of Information Processing and Intelligent Control (Minjiang University), Fuzhou, China

    Wayne Xin Zhao

  4. School of Computer Science and Engineering, Nanyang Technological University, Singapore, Singapore

    Aixin Sun & Jialong Han

  5. HTC Research & Healthcare, San Francisco, CA, USA

    Edward Y. Chang

Authors
  1. Wayne Xin Zhao
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Ningnan Zhou
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Aixin Sun
    View author publications

    You can also search for this author inPubMed Google Scholar

  4. Ji-Rong Wen
    View author publications

    You can also search for this author inPubMed Google Scholar

  5. Jialong Han
    View author publications

    You can also search for this author inPubMed Google Scholar

  6. Edward Y. Chang
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence to Jialong Han.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Zhao, W.X., Zhou, N., Sun, A. et al. A time-aware trajectory embedding model for next-location recommendation. Knowl Inf Syst 56, 559–579 (2018). https://doi.org/10.1007/s10115-017-1107-4

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10115-017-1107-4

Keywords