ABSTRACT
Behavioral pattern discovery is increasingly being studied to understand human behavior and the discovered patterns can be used in many real world applications such as web search, recommender system and advertisement targeting. Traditional methods usually consider the behaviors as simple user and item connections, or represent them with a static model. In real world, however, human behaviors are actually complex and dynamic: they include correlations between user and multiple types of objects and also continuously evolve along time. These characteristics cause severe data sparsity and computational complexity problem, which pose great challenge to human behavioral analysis and prediction. In this paper, we propose a Flexible Evolutionary Multi-faceted Analysis (FEMA) framework for both behavior prediction and pattern mining. FEMA utilizes a flexible and dynamic factorization scheme for analyzing human behavioral data sequences, which can incorporate various knowledge embedded in different object domains to alleviate the sparsity problem. We give approximation algorithms for efficiency, where the bound of approximation loss is theoretically proved. We extensively evaluate the proposed method in two real datasets. For the prediction of human behaviors, the proposed FEMA significantly outperforms other state-of-the-art baseline methods by 17.4%. Moreover, FEMA is able to discover quite a number of interesting multi-faceted temporal patterns on human behaviors with good interpretability. More importantly, it can reduce the run time from hours to minutes, which is significant for industry to serve real-time applications.
Supplemental Material
- E. Acar, D. M. Dunlavy, T. G. Kolda, and M. Mørup. Scalable tensor factorizations for incomplete data. Chemometrics and Intelligent Laboratory Systems, 106(1):41--56, 2011.Google ScholarCross Ref
- W. Chen, W. Hsu, and M. L. Lee. Making recommendations from multiple domains. In KDD'13, pages 892--900. Google ScholarDigital Library
- W. Chen, W. Hsu, and M. L. Lee. Modeling user's receptiveness over time for recommendation. In SIGIR'13, pages 373--382. Google ScholarDigital Library
- A. Cichocki and R. Zdunek. Regularized alternating least squares algorithms for non-negative matrix/tensor factorization. In Advances in Neural Networks--ISNN 2007, pages 793--802. Google ScholarDigital Library
- P. Cui, S. Jin, L. Yu, F. Wang, W. Zhu, and S. Yang. Cascading outbreak prediction in networks: a data-driven approach. In KDD'13, pages 901--909. Google ScholarDigital Library
- P. Cui, F. Wang, S. Liu, M. Ou, S. Yang, and L. Sun. Who should share what? item-level social influence prediction for users and posts ranking. In SIGIR'11, pages 185--194. Google ScholarDigital Library
- J. Davis and M. Goadrich. The relationship between precision-recall and roc curves. In ICML'06, pages 233--240. Google ScholarDigital Library
- L. De Lathauwer, B. De Moor, and J. Vandewalle. A multilinear singular value decomposition. SIAM journal on Matrix Analysis and Applications, 21(4):1253--1278, 2000. Google ScholarDigital Library
- D. M. Dunlavy, T. G. Kolda, and E. Acar. Temporal link prediction using matrix and tensor factorizations. TKDD, 5(2):10, 2011. Google ScholarDigital Library
- L. Hu, J. Cao, G. Xu, L. Cao, Z. Gu, and C. Zhu. Personalized recommendation via cross-domain triadic factorization. In WWW'13, pages 595--606. Google ScholarDigital Library
- M. Jiang, P. Cui, R. Liu, Q. Yang, F. Wang, W. Zhu, and S. Yang. Social contextual recommendation. In CIKM'12, pages 45--54. Google ScholarDigital Library
- M. Jiang, P. Cui, F. Wang, Q. Yang, W. Zhu, and S. Yang. Social recommendation across multiple relational domains. In CIKM'12, pages 1422--1431. Google ScholarDigital Library
- U. Kang, E. Papalexakis, A. Harpale, and C. Faloutsos. Gigatensor: scaling tensor analysis up by 100 times-algorithms and discoveries. In KDD'12, pages 316--324. Google ScholarDigital Library
- G. Karypis. Evaluation of item-based top-n recommendation algorithms. In CIKM'01, pages 247--254. Google ScholarDigital Library
- T. G. Kolda. Orthogonal tensor decompositions. SIAM Journal on Matrix Analysis and Applications, 23(1):243--255, 2001. Google ScholarDigital Library
- T. G. Kolda and B. W. Bader. Tensor decompositions and applications. SIAM review, 51(3):455--500, 2009. Google ScholarDigital Library
- T. G. Kolda and J. Sun. Scalable tensor decompositions for multi-aspect data mining. In ICDM'08, pages 363--372. Google ScholarDigital Library
- Y. Koren, R. Bell, and C. Volinsky. Matrix factorization techniques for recommender systems. Computer, 42(8):30--37, 2009. Google ScholarDigital Library
- L. Liu, J. Tang, J. Han, M. Jiang, and S. Yang. Mining topic-level influence in heterogeneous networks. In CIKM'10, pages 199--208. Google ScholarDigital Library
- K. Narang, S. Nagar, S. Mehta, L. Subramaniam, and K. Dey. Discovery and analysis of evolving topical social discussions on unstructured microblogs. In Advances in Information Retrieval, pages 545--556. 2013. Google ScholarDigital Library
- H. Rachlin. The value of temporal patterns in behavior. Current Directions in Psychological Science, 1995.Google ScholarCross Ref
- K. Radinsky, K. M. Svore, S. T. Dumais, M. Shokouhi, J. Teevan, A. Bocharov, and E. Horvitz. Behavioral dynamics on the web: Learning, modeling, and prediction. TOIS, 31(3):16, 2013. Google ScholarDigital Library
- S. Rendle and L. Schmidt-Thieme. Pairwise interaction tensor factorization for personalized tag recommendation. In WSDM'10, pages 81--90. Google ScholarDigital Library
- S. B. Roy, M. De Cock, V. Mandava, S. Savanna, B. Dalessandro, C. Perlich, W. Cukierski, and B. Hamner. The microsoft academic search dataset and kdd cup 2013. In Proceedings of the KDD Cup 2013 Workshop. Google ScholarDigital Library
- G. W. Stewart and J.-g. Sun. Matrix perturbation theory.Google Scholar
- J. Sun, D. Tao, S. Papadimitriou, P. S. Yu, and C. Faloutsos. Incremental tensor analysis: Theory and applications. TKDD, 2(3):11, 2008. Google ScholarDigital Library
- J.-T. Sun, H.-J. Zeng, H. Liu, Y. Lu, and Z. Chen. Cubesvd: a novel approach to personalized web search. In WWW'05, pages 382--390. Google ScholarDigital Library
- Y. Sun, J. Tang, J. Han, C. Chen, and M. Gupta. Co-evolution of multi-typed objects in dynamic star networks. TKDE, 2013.Google Scholar
- P. Symeonidis, A. Nanopoulos, and Y. Manolopoulos. Tag recommendations based on tensor dimensionality reduction. In RecSys'08, pages 43--50. Google ScholarDigital Library
- F. Wang, J. Sun, J. Hu, and S. Ebadollahi. imet: interactive metric learning in healthcare applications. In SDM'11, pages 944--955.Google Scholar
- F. Wang, H. Tong, and C.-Y. Lin. Towards evolutionary nonnegative matrix factorization. In AAAI'11, pages 501--506.Google Scholar
- X. Wang, C. Zhai, and D. Roth. Understanding evolution of research themes: a probabilistic generative model for citations. In KDD'13, pages 1115--1123. Google ScholarDigital Library
- L. Xiang, Q. Yuan, S. Zhao, L. Chen, X. Zhang, Q. Yang, and J. Sun. Temporal recommendation on graphs via long-and short-term preference fusion. In KDD'10, pages 723--732. Google ScholarDigital Library
- Q. Yuan, G. Cong, Z. Ma, A. Sun, and N. M. Thalmann. Who, where, when and what: Discover spatio-temporal topics for twitter users. In KDD'13, pages 605--613. Google ScholarDigital Library
- X. Zheng, H. Ding, H. Mamitsuka, and S. Zhu. Collaborative matrix factorization with multiple similarities for predicting drug-target interactions. In KDD'13, pages 1025--1033. Google ScholarDigital Library
Index Terms
- FEMA: flexible evolutionary multi-faceted analysis for dynamic behavioral pattern discovery
Recommendations
Collaborative filtering with weighted opinion aspects
Collaborative filtering (CF) aims to produce recommendations based on other users' ratings to an item. Most existing CF methods rely on the overall ratings an item has received. However, these ratings alone sometimes cannot provide sufficient ...
A Time-Aware Personalized Point-of-Interest Recommendation via High-Order Tensor Factorization
Special issue: Search, Mining and their Applications on Mobile DevicesRecently, location-based services (LBSs) have been increasingly popular for people to experience new possibilities, for example, personalized point-of-interest (POI) recommendations that leverage on the overlapping of user trajectories to recommend POI ...
Behavior Informatics to Discover Behavior Insight for Active and Tailored Client Management
KDD '17: Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data MiningBehavior is ubiquitous, and behavior intelligence and insight play an important role in data understanding and business problem-solving. Behavior Informatics [1,2] emerges as an important tool for discovering behavior intelligence and behavior insight. ...
Comments