Sha Li
ABSTRACT
Understanding and predicting user behavior on online platforms has proved to be of significant value, with applications spanning from targeted advertising, political campaigning, anomaly detection to user self-monitoring. With the growing functionality and flexibility of online platforms, users can now accomplish a variety of tasks online. This advancement has rendered many previous works that focus on modeling a single type of activity obsolete. In this work, we target this new problem by modeling the interplay between the time series of different types of activities and apply our model to predict future user behavior. Our model, FM-Hawkes, stands for Fourier-based kernel multi-dimensional Hawkes process. Specifically, we model the multiple activity time series as a multi-dimensional Hawkes process. The correlations between different types of activities are then captured by the influence factor. As for the temporal triggering kernel, we observe that the intensity function consists of numerous kernel functions with time shift. Thus, we employ a Fourier transformation based non-parametric estimation. Our model is not bound to any particular platform and explicitly interprets the causal relationship between actions. By applying our model to real-life datasets, we confirm that the mutual excitation effect between different activities prevails among users. Prediction results show our superiority over models that do not consider action types and flexible kernels
- Emmanuel Bacry, Khalil Dayri, and Jean-François Muzy. 2012. Non-parametric kernel estimation for symmetric Hawkes processes. Application to high frequency fnancial data. EPJ B 85, 5 (2012), 1--12.Google Scholar
Cross Ref
- Peng Bao. 2016. Modeling and Predicting Popularity Dynamics via an Infuencebased Self-Excited Hawkes Process. In CIKM. ACM, 1897--1900. Google ScholarDigital Library
- Ye Chen, Dmitry Pavlov, and John F. Canny. 2009. Large-scale behavioral targeting. In KDD. 209--218. Google ScholarDigital Library
- Alceu Ferraz Costa, Agma Juci Machado Traina, Caetano Traina Jr., and Christos Faloutsos. 2016. Vote-and-Comment: Modeling the Coevolution of User Interactions in Social Voting Web Sites. In ICDM. 91--100.Google Scholar
- Alceu Ferraz Costa, Yuto Yamaguchi, Agma J. M. Traina, Caetano Traina, and Christos Faloutsos. 2015. RSC: Mining and Modeling Temporal Activity in Social Media. In KDD. Google ScholarDigital Library
- Rodrigo Augusto da Silva Alves, Renato Martins Assunğão, and Pedro O. S. Vaz de Melo. 2016. Burstiness Scale: A Parsimonious Model for Characterizing Random Series of Events. In KDD.Google Scholar
- A.S.C. Ehrenberg. 1959. The pattern of consumer purchases. Applied Statistics 8(1) (1959), 26--41.Google Scholar
- Michael Eichler, Rainer Dahlhaus, and Johannes Dueck. 2016. Graphical modeling for multivariate hawkes processes with nonparametric link functions. J. Time Ser. Anal. (2016).Google Scholar
- Mehrdad Farajtabar, Yichen Wang, Manuel Gomez-Rodriguez, Shuang Li, Hongyuan Zha, and Le Song. 2015. COEVOLVE: A Joint Point Process Model for Information Difusion and Network Co-evolution. In NIPS. Google ScholarDigital Library
- Scott A. Golder, Dennis M. Wilkinson, and Bernardo A. Huberman. 2007. Rhythms of social interaction: messaging within a massive online network. C&T (2007), 41--66.Google Scholar
- Niels Richard Hansen, Patricia Reynaud-Bouret, Vincent Rivoirard, et al. 2015. Lasso and probabilistic inequalities for multivariate point processes. Bernoulli 21, 1 (2015), 83--143.Google ScholarCross Ref
- Stephen Hardiman, Nicolas Bercot, and Jean-Philippe Bouchaud. 2013. Critical refexivity in fnancial markets: a Hawkes process analysis. (2013).Google Scholar
- Alan G Hawkes. 1971. Spectra of some self-exciting and mutually exciting point processes. Biometrika (1971), 83--90.Google Scholar
- Hideaki Kim, Noriko Takaya, and Hiroshi Sawada. 2014. Tracking Temporal Dynamics of Purchase Decisions via Hierarchical Time-Rescaling Model. In CIKM. 1389--1398. Google ScholarDigital Library
- Remi Lemonnier and Nicolas Vayatis. 2014. Nonparametric markovian learning of triggering kernels for mutually exciting and mutually inhibiting multivariate hawkes processes. In ECML PKDD. 161--176. Google ScholarDigital Library
- Erik Lewis, George Mohler, P Jefrey Brantingham, and Andrea L Bertozzi. 2012. Self-exciting point process models of civilian deaths in Iraq. Security Journal 25, 3 (2012), 244--264.Google ScholarCross Ref
- Michal Lukasik, P. K. Srijith, Duy Vu, Kalina Bontcheva, Arkaitz Zubiaga, and Trevor Cohn. 2016. Hawkes Processes for Continuous Time Sequence Classifcation: an Application to Rumour Stance Classifcation in Twitter. In ACL (2). The Association for Computer Linguistics.Google Scholar
- Dixin Luo, Hongteng Xu, Yi Zhen, Xia Ning, Hongyuan Zha, Xiaokang Yang, and Wenjun Zhang. 2015. Multi-task multi-dimensional hawkes processes for modeling event sequences. In IJCAI. 3685--3691. Google ScholarDigital Library
- R. Dean Malmgren, Jake M. Hofman, Luis A. Nunes Amaral, and Duncan J. Watts. 2009. Characterizing individual communication patterns. In KDD. Google ScholarDigital Library
- David Marsan and Olivier Lengline. 2008. Extending earthquakes' reach through cascading. Science 319, 5866 (2008), 1076--1079.Google Scholar
- Swapnil Mishra, Marian-Andrei Rizoiu, and Lexing Xie. 2016. Feature Driven and Point Process Approaches for Popularity Prediction. In CIKM. ACM, 1069--1078. Google ScholarDigital Library
- Yosihiko Ogata. 1981. On Lewis' simulation method for point processes. IEEE Transactions on Information Theory 27, 1 (1981), 23--31. Google ScholarDigital Library
- Sarah Masud Preum, John A. Stankovic, and Yanjun Qi. 2015. MAPer: A Multiscale Adaptive Personalized Model for Temporal Human Behavior Prediction. In CIKM. 433--442. Google ScholarDigital Library
- Marian-Andrei Rizoiu, Lexing Xie, Scott Sanner, Manuel Cebrián, Honglin Yu, and Pascal Van Hentenryck. 2017. Expecting to be HIP: Hawkes Intensity Processes for Social Media Popularity. In WWW. ACM, 735--744. Google ScholarDigital Library
- Hongteng Xu, Mehrdad Farajtabar, and Hongyuan Zha. 2016. Learning Granger Causality for Hawkes Processes. In ICML, Vol. 48. 1717--1726. Google ScholarDigital Library
- Qingyuan Zhao, Murat A. Erdogdu, Hera Y. He, Anand Rajaraman, and Jure Leskovec. 2015. SEISMIC: A Self-Exciting Point Process Model for Predicting Tweet Popularity. In KDD. ACM, 1513--1522. Google ScholarDigital Library
- Ke Zhou, Hongyuan Zha, and Le Song. 2013. Learning Triggering Kernels for Multi-dimensional Hawkes Processes. In ICML. Google ScholarDigital Library
- Yin Zhu, Erheng Zhong, Sinno Jialin Pan, Xiao Wang, Minzhe Zhou, and Qiang Yang. 2013. Predicting user activity level in social networks. In CIKM. 159--168. Google ScholarDigital Library
Index Terms
- FM-Hawkes: A Hawkes Process Based Approach for Modeling Online Activity Correlations
Recommendations
Forecasting the behavior of an elderly using wireless sensors data in a smart home
In this paper, the ability to determine the wellness of an elderly living alone in a smart home using a low-cost, robust, flexible and data driven intelligent system is presented. A framework integrating temporal and spatial contextual information for ...
Modelling Bid and Ask Prices Using Constrained Hawkes Processes: Ergodicity and Scaling Limit
We introduce a multivariate point process describing the dynamics of the Bid and Ask price of a financial asset. The point process is similar to a Hawkes process, with additional constraints on its intensity corresponding to the natural ordering of the best ...
On the Causal Effect of Badges
WWW '18: Proceedings of the 2018 World Wide Web ConferenceA wide variety of online platforms use digital badges to encourage users to take certain types of desirable actions. However, despite their growing popularity, their causal effect on users» behavior is not well understood. This is partly due to the lack ...
Comments