ABSTRACT
Mobility prediction enables appealing proactive experiences for location-aware services and offers essential intelligence to business and governments. Recent studies suggest that human mobility is highly regular and predictable. Additionally, social conformity theory indicates that people's movements are influenced by others. However, existing approaches for location prediction fail to organically combine both the regularity and conformity of human mobility in a unified model, and lack the capacity to incorporate heterogeneous mobility datasets to boost prediction performance. To address these challenges, in this paper we propose a hybrid predictive model integrating both the regularity and conformity of human mobility as well as their mutual reinforcement. In addition, we further elevate the predictive power of our model by learning location profiles from heterogeneous mobility datasets based on a gravity model. We evaluate the proposed model using several city-scale mobility datasets including location check-ins, GPS trajectories of taxis, and public transit data. The experimental results validate that our model significantly outperforms state-of-the-art approaches for mobility prediction in terms of multiple metrics such as accuracy and percentile rank. The results also suggest that the predictability of human mobility is time-varying, e.g., the overall predictability is higher on workdays than holidays while predicting users' unvisited locations is more challenging for workdays than holidays.
Supplemental Material
- D. Ashbrook and T. Starner. Using GPS to learn significant locations and predict movement across multiple users. phPersonal and Ubiquitous Computing, 7 (5): 275--286, 2003. Google ScholarDigital Library
- J. P. Attanucci and N. H. Wilson. Bus passenger origin-destination estimation and related analyses using automated data collection systems. phJournal of Public Transportation, 14 (4): 131, 2011.Google ScholarCross Ref
- lves, Hu, Ramasco, and Vespignani}Gravity_exampleD. Balcan, V. Colizza, B. Gonçalves, H. Hu, J. J. Ramasco, and A. Vespignani. Multiscale mobility networks and the spatial spreading of infectious diseases. phProceedings of the National Academy of Sciences, 106 (51): 21484--21489, 2009.Google ScholarCross Ref
- J. Chang and E. Sun. Location 3: How users share and respond to location-based data on social networking sites. In phProceedings of the Fifth International AAAI Conference on Weblogs and Social Media, pages 74--80, 2011.Google Scholar
- C. Cheng, H. Yang, I. King, and M. R. Lyu. Fused matrix factorization with geographical and social influence in location-based social networks. In phAAAI, volume 12, page 1, 2012.Google Scholar
- E. Cho, S. A. Myers, and J. Leskovec. Friendship and mobility: user movement in location-based social networks. In phProceedings of the 17th ACM SIGKDD international conference on Knowledge discovery and data mining, pages 1082--1090. ACM, 2011. Google ScholarDigital Library
- R. B. Cialdini and N. J. Goldstein. Social influence: Compliance and conformity. phAnnual review of psychology, 55: 591--621, 2004.Google Scholar
- Y.-A. de Montjoye, C. A. Hidalgo, M. Verleysen, and V. D. Blondel. Unique in the crowd: The privacy bounds of human mobility. phScientific reports, 3, 2013.Google Scholar
- N. Eagle and A. S. Pentland. Eigenbehaviors: Identifying structure in routine. phBehavioral Ecology and Sociobiology, 63 (7): 1057--1066, 2009.Google ScholarCross Ref
- Gao, Tang, and Liu}Spatio-temporal_modelH. Gao, J. Tang, and H. Liu. Mobile location prediction in spatio-temporal context. In phNokia mobile data challenge workshop. Citeseer, 2012\natexlaba.Google Scholar
- Gao, Tang, and Liu}prediction_gscorr_GaoH. Gao, J. Tang, and H. Liu. gSCorr: modeling geo-social correlations for new check-ins on location-based social networks. In phProceedings of the 21st ACM international conference on Information and knowledge management, pages 1582--1586. ACM, 2012\natexlabb. Google ScholarDigital Library
- Gao, Tang, and Liu}social_ties_GaoH. Gao, J. Tang, and H. Liu. Exploring social-historical ties on location-based social networks. In phICWSM, 2012\natexlabc.Google Scholar
- M. C. Gonzalez, C. A. Hidalgo, and A.-L. Barabasi. Understanding individual human mobility patterns. phNature, 453 (7196): 779--782, 2008.Google ScholarCross Ref
- H. H. Kelejian and I. R. Prucha. Specification and estimation of spatial autoregressive models with autoregressive and heteroskedastic disturbances. phJournal of Econometrics, 157 (1): 53--67, 2010.Google ScholarCross Ref
- M. Kim and D. Kotz. Periodic properties of user mobility and access-point popularity. phPersonal and Ubiquitous Computing, 11 (6): 465--479, 2007. Google ScholarDigital Library
- Y.-J. Kim and S.-B. Cho. A HMM-based location prediction framework with location recognizer combining k-nearest neighbor and multiple decision trees. In phHybrid Artificial Intelligent Systems, pages 618--628. Springer, 2013.Google Scholar
- Y. Koren, R. Bell, and C. Volinsky. Matrix factorization techniques for recommender systems. phComputer, 42 (8): 30--37, 2009. Google ScholarDigital Library
- Z. Li, B. Ding, J. Han, R. Kays, and P. Nye. Mining periodic behaviors for moving objects. In phProceedings of the 16th ACM SIGKDD international conference on Knowledge discovery and data mining, pages 1099--1108. ACM, 2010. Google ScholarDigital Library
- Lian, Xie, Zheng, Yuan, Zhang, and Chen}Prediction_DoveD. Lian, X. Xie, V. W. Zheng, N. J. Yuan, F. Zhang, and E. Chen. CEPR: A collaborative exploration and periodically returning model for location prediction. phACM Transactions on Intelligent Systems and Technology (TIST), 6 (1), 2014\natexlaba. Google ScholarDigital Library
- Lian, Zhao, Xie, Sun, Chen, and Rui}Recommendation_DoveD. Lian, C. Zhao, X. Xie, G. Sun, E. Chen, and Y. Rui. Geomf: joint geographical modeling and matrix factorization for point-of-interest recommendation. In phProceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining, pages 831--840. ACM, 2014\natexlabb. Google ScholarDigital Library
- B. Liu, Y. Fu, Z. Yao, and H. Xiong. Learning geographical preferences for point-of-interest recommendation. In phProceedings of the 19th ACM SIGKDD international conference on Knowledge discovery and data mining, pages 1043--1051. ACM, 2013. Google ScholarDigital Library
- Y. Liu, W. Wei, A. Sun, and C. Miao. Exploiting geographical neighborhood characteristics for location recommendation. In phProceedings of the 23rd ACM International Conference on Conference on Information and Knowledge Management, pages 739--748. ACM, 2014. Google ScholarDigital Library
- A. Monreale, F. Pinelli, R. Trasarti, and F. Giannotti. Wherenext: a location predictor on trajectory pattern mining. In phProceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining, pages 637--646. ACM, 2009. Google ScholarDigital Library
- A. Noulas, S. Scellato, C. Mascolo, and M. Pontil. An empirical study of geographic user activity patterns in foursquare. phICWSM, 11: 70--573, 2011.Google Scholar
- A. Noulas, S. Scellato, N. Lathia, and C. Mascolo. Mining user mobility features for next place prediction in location-based services. In phICDM, pages 1038--1043. Citeseer, 2012. Google ScholarDigital Library
- A. Sadilek, H. Kautz, and J. P. Bigham. Finding your friends and following them to where you are. In phProceedings of the fifth ACM international conference on Web search and data mining, pages 723--732. ACM, 2012. Google ScholarDigital Library
- S. Scellato, M. Musolesi, C. Mascolo, V. Latora, and A. T. Campbell. Nextplace: a spatio-temporal prediction framework for pervasive systems. In phPervasive Computing, pages 152--169. Springer, 2011. Google ScholarDigital Library
- S. Scellato, A. Noulas, R. Lambiotte, and C. Mascolo. Socio-spatial properties of online location-based social networks. phICWSM, 11: 329--336, 2011.Google Scholar
- M. N. Schmidt, O. Winther, and L. K. Hansen. Bayesian non-negative matrix factorization. In phIndependent Component Analysis and Signal Separation, pages 540--547. Springer, 2009. Google ScholarDigital Library
- J. Scott, A. Bernheim Brush, J. Krumm, B. Meyers, M. Hazas, S. Hodges, and N. Villar. Preheat: controlling home heating using occupancy prediction. In phProceedings of the 13th international conference on Ubiquitous computing, pages 281--290. ACM, 2011. Google ScholarDigital Library
- N. Simon, J. Friedman, T. Hastie, and R. Tibshirani. A sparse-group lasso. phJournal of Computational and Graphical Statistics, 22 (2): 231--245, 2013.Google ScholarCross Ref
- C. Song, T. Koren, P. Wang, and A.-L. Barabási. Modelling the scaling properties of human mobility. phNature Physics, 6 (10): 818--823, 2010.Google ScholarCross Ref
- C. Song, Z. Qu, N. Blumm, and A.-L. Barabási. Limits of predictability in human mobility. phScience, 327 (5968): 1018--1021, 2010.Google ScholarCross Ref
- L. Song, D. Kotz, R. Jain, and X. He. Evaluating location predictors with extensive wi-fi mobility data. In phINFOCOM 2004. Twenty-third AnnualJoint Conference of the IEEE Computer and Communications Societies, volume 2, pages 1414--1424. IEEE, 2004.Google Scholar
- D. Wang, D. Pedreschi, C. Song, F. Giannotti, and A.-L. Barabasi. Human mobility, social ties, and link prediction. In phProceedings of the 17th ACM SIGKDD international conference on Knowledge discovery and data mining, pages 1100--1108. ACM, 2011. Google ScholarDigital Library
- A. G. Wilson. A statistical theory of spatial distribution models. phTransportation research, 1 (3): 253--269, 1967.Google Scholar
- J. Ye, Z. Zhu, and H. Cheng. What's your next move: User activity prediction in location-based social networks. In phProc. of SIAM International Conference on Data Mining (SDM), 2013.Google Scholar
- N. J. Yuan, Y. Zheng, X. Xie, Y. Wang, K. Zheng, and H. Xiong. Discovering urban functional zones using latent activity trajectories. phIEEE Transactions on Knowledge & Data Engineering, 27 (3): 712--725.Google Scholar
- Yuan, Wang, Zhang, Xie, and Sun}Smart_card_1_NicholasN. J. Yuan, Y. Wang, F. Zhang, X. Xie, and G. Sun. Reconstructing individual mobility from smart card transactions: A space alignment approach. In phData Mining (ICDM), 2013 IEEE 13th International Conference on, pages 877--886. IEEE, 2013\natexlaba.Google Scholar
- Yuan, Cong, Ma, Sun, and Thalmann}W4_tweetsQ. Yuan, G. Cong, Z. Ma, A. Sun, and N. M. Thalmann. Who, where, when and what: discover spatio-temporal topics for twitter users. In phProceedings of the 19th ACM SIGKDD international conference on Knowledge discovery and data mining, pages 605--613. ACM, 2013\natexlabb. Google ScholarDigital Library
- Y. Zheng, Q. Li, Y. Chen, X. Xie, and W.-Y. Ma. Understanding mobility based on gps data. In phProceedings of the 10th international conference on Ubiquitous computing, pages 312--321. ACM, 2008. Google ScholarDigital Library
Index Terms
- Regularity and Conformity: Location Prediction Using Heterogeneous Mobility Data
Recommendations
DeepMove: Predicting Human Mobility with Attentional Recurrent Networks
WWW '18: Proceedings of the 2018 World Wide Web ConferenceHuman mobility prediction is of great importance for a wide spectrum of location-based applications. However, predicting mobility is not trivial because of three challenges: 1) the complex sequential transition regularities exhibited with time-dependent ...
GeoMF: joint geographical modeling and matrix factorization for point-of-interest recommendation
KDD '14: Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data miningPoint-of-Interest (POI) recommendation has become an important means to help people discover attractive locations. However, extreme sparsity of user-POI matrices creates a severe challenge. To cope with this challenge, viewing mobility records on ...
Geography-Aware Sequential Location Recommendation
KDD '20: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data MiningSequential location recommendation plays an important role in many applications such as mobility prediction, route planning and location-based advertisements. In spite of evolving from tensor factorization to RNN-based neural networks, existing methods ...
Comments