Markov-modulated Marked Poisson Processes for Check-in Data

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.

[1]  J. Antonio García-Macías,et al.  Learning and user adaptation in location forecasting , 2013, UbiComp.

[2]  L. Breuer.  Introduction to Stochastic Processes , 2022, Statistical Methods for Climate Scientists.

[3]  Stuart J. Russell,et al.  Dynamic bayesian networks: representation, inference and learning , 2002 .

[4]  S. Frühwirth-Schnatter.  Data Augmentation and Dynamic Linear Models , 1994 .

[5]  Carl E. Rasmussen,et al.  Factorial Hidden Markov Models , 1997 .

[6]  Lidan Shou,et al.  Splitter: Mining Fine-Grained Sequential Patterns in Semantic Trajectories , 2014, Proc. VLDB Endow..

[7]  P. Fearnhead,et al.  An exact Gibbs sampler for the Markov‐modulated Poisson process , 2006 .

[8]  Michael I. Jordan,et al.  Factorial Hidden Markov Models , 1995, Machine Learning.

[9]  Ardavan Saeedi,et al.  Priors over Recurrent Continuous Time Processes , 2011, NIPS.

[10]  Michael I. Jordan,et al.  Hierarchical Dirichlet Processes , 2006 .

[11]  Asger Hobolth,et al.  SIMULATION FROM ENDPOINT-CONDITIONED, CONTINUOUS-TIME MARKOV CHAINS ON A FINITE STATE SPACE, WITH APPLICATIONS TO MOLECULAR EVOLUTION. , 2009, The annals of applied statistics.

[12]  W. Eric L. Grimson,et al.  Trajectory Analysis and Semantic Region Modeling Using Nonparametric Hierarchical Bayesian Models , 2011, International Journal of Computer Vision.

[13]  Xing Xie,et al.  Mining interesting locations and travel sequences from GPS trajectories , 2009, WWW '09.

[14]  Dino Pedreschi,et al.  Trajectory pattern mining , 2007, KDD '07.

[15]  Chris Chatfield,et al.  Introduction to Statistical Time Series. , 1976 .

[16]  Xing Xie,et al.  T-drive: driving directions based on taxi trajectories , 2010, GIS '10.

[17]  Philipp Metzner,et al.  Generator estimation of Markov jump processes based on incomplete observations nonequidistant in time. , 2007, Physical review. E, Statistical, nonlinear, and soft matter physics.

[18]  Yee Whye Teh,et al.  MCMC for continuous-time discrete-state systems , 2012, NIPS.

[19]  Lawrence R. Rabiner,et al.  A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.

[20]  Shane G. Henderson,et al.  Travel time estimation for ambulances using Bayesian data augmentation , 2013, 1312.1873.

[21]  Yu Zheng,et al.  Travel time estimation of a path using sparse trajectories , 2014, KDD.

[22]  Christian S. Jensen,et al.  Discovery of convoys in trajectory databases , 2008, Proc. VLDB Endow..

[23]  Yee Whye Teh,et al.  Fast MCMC sampling for Markov jump processes and extensions , 2012, J. Mach. Learn. Res..

[24]  Jiawei Han,et al.  Swarm: Mining Relaxed Temporal Moving Object Clusters , 2010, Proc. VLDB Endow..

[25]  Huan Liu,et al.  gSCorr: modeling geo-social correlations for new check-ins on location-based social networks , 2012, CIKM.

[26]  Michael I. Jordan,et al.  Latent Dirichlet Allocation , 2001, J. Mach. Learn. Res..

[27]  Jiliang Tang,et al.  Mobile Location Prediction in Spatio-Temporal Context , 2012 .

[28]  Patrick Laube,et al.  Analyzing Relative Motion within Groups of Trackable Moving Point Objects , 2002, GIScience.

[29]  Xing Xie,et al.  Solving the data sparsity problem in destination prediction , 2015, The VLDB Journal.

[30]  Padhraic Smyth,et al.  Learning to detect events with Markov-modulated poisson processes , 2007, TKDD.

[31]  Padhraic Smyth,et al.  Modeling human location data with mixtures of kernel densities , 2014, KDD.

[32]  M. Bladt,et al.  Statistical inference for discretely observed Markov jump processes , 2005 .

[33]  Bruno Martins,et al.  Predicting future locations with hidden Markov models , 2012, UbiComp.