Markov-modulated Marked Poisson Processes for Check-in Data

Jiangwei Pan, Vinayak Rao, Pankaj Agarwal, Alan Gelfand
Proceedings of The 33rd International Conference on Machine Learning, PMLR 48:2244-2253, 2016.

Abstract

We develop continuous-time probabilistic models to study trajectory data consisting of times and locations of user “check-ins”. We model the data as realizations of a marked point process, with intensity and mark-distribution modulated by a latent Markov jump process (MJP). We also include user-heterogeneity in our model by assigning each user a vector of “preferred locations”. Our model extends latent Dirichlet allocation by dropping the bag-of-words assumption and operating in continuous time. We show how an appropriate choice of priors allows efficient posterior inference. Our experiments demonstrate the usefulness of our approach by comparing with various baselines on a variety of tasks.

Cite this Paper


BibTeX
@InProceedings{pmlr-v48-pana16, title = {Markov-modulated Marked Poisson Processes for Check-in Data}, author = {Pan, Jiangwei and Rao, Vinayak and Agarwal, Pankaj and Gelfand, Alan}, booktitle = {Proceedings of The 33rd International Conference on Machine Learning}, pages = {2244--2253}, year = {2016}, editor = {Balcan, Maria Florina and Weinberger, Kilian Q.}, volume = {48}, series = {Proceedings of Machine Learning Research}, address = {New York, New York, USA}, month = {20--22 Jun}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v48/pana16.pdf}, url = {https://proceedings.mlr.press/v48/pana16.html}, abstract = {We develop continuous-time probabilistic models to study trajectory data consisting of times and locations of user “check-ins”. We model the data as realizations of a marked point process, with intensity and mark-distribution modulated by a latent Markov jump process (MJP). We also include user-heterogeneity in our model by assigning each user a vector of “preferred locations”. Our model extends latent Dirichlet allocation by dropping the bag-of-words assumption and operating in continuous time. We show how an appropriate choice of priors allows efficient posterior inference. Our experiments demonstrate the usefulness of our approach by comparing with various baselines on a variety of tasks.} }
Endnote
%0 Conference Paper %T Markov-modulated Marked Poisson Processes for Check-in Data %A Jiangwei Pan %A Vinayak Rao %A Pankaj Agarwal %A Alan Gelfand %B Proceedings of The 33rd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2016 %E Maria Florina Balcan %E Kilian Q. Weinberger %F pmlr-v48-pana16 %I PMLR %P 2244--2253 %U https://proceedings.mlr.press/v48/pana16.html %V 48 %X We develop continuous-time probabilistic models to study trajectory data consisting of times and locations of user “check-ins”. We model the data as realizations of a marked point process, with intensity and mark-distribution modulated by a latent Markov jump process (MJP). We also include user-heterogeneity in our model by assigning each user a vector of “preferred locations”. Our model extends latent Dirichlet allocation by dropping the bag-of-words assumption and operating in continuous time. We show how an appropriate choice of priors allows efficient posterior inference. Our experiments demonstrate the usefulness of our approach by comparing with various baselines on a variety of tasks.
RIS
TY - CPAPER TI - Markov-modulated Marked Poisson Processes for Check-in Data AU - Jiangwei Pan AU - Vinayak Rao AU - Pankaj Agarwal AU - Alan Gelfand BT - Proceedings of The 33rd International Conference on Machine Learning DA - 2016/06/11 ED - Maria Florina Balcan ED - Kilian Q. Weinberger ID - pmlr-v48-pana16 PB - PMLR DP - Proceedings of Machine Learning Research VL - 48 SP - 2244 EP - 2253 L1 - http://proceedings.mlr.press/v48/pana16.pdf UR - https://proceedings.mlr.press/v48/pana16.html AB - We develop continuous-time probabilistic models to study trajectory data consisting of times and locations of user “check-ins”. We model the data as realizations of a marked point process, with intensity and mark-distribution modulated by a latent Markov jump process (MJP). We also include user-heterogeneity in our model by assigning each user a vector of “preferred locations”. Our model extends latent Dirichlet allocation by dropping the bag-of-words assumption and operating in continuous time. We show how an appropriate choice of priors allows efficient posterior inference. Our experiments demonstrate the usefulness of our approach by comparing with various baselines on a variety of tasks. ER -
APA
Pan, J., Rao, V., Agarwal, P. & Gelfand, A.. (2016). Markov-modulated Marked Poisson Processes for Check-in Data. Proceedings of The 33rd International Conference on Machine Learning, in Proceedings of Machine Learning Research 48:2244-2253 Available from https://proceedings.mlr.press/v48/pana16.html.

Related Material