Predictive Population Behavior Analysis from Multiple Contexts with Multilinear Poisson Regression
Masamichi Shimosaka (Tokyo Tech), Takeshi Tsukiji (UTokyo), Hideyuki Wada(UTokyo), Kota Tsubouchi
The ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems 2018 (ACM SIGSPATIAL 2018), 2018/11
Machine Learning Data Science Misc.
- Predicting behaviors of a population from location-oriented log data from smartphones, i.e., urban population dynamics, has become more common in mobile and pervasive computing. A bilinear representation approach has been proposed to improve the prediction accuracy of urban population dynamics by adding contexts such as geographical information and day of the week. However, this approach has a strong limitation in that additional contexts can not be directly utilized in this representation with a unified manner. To resolve this issue, we propose a new predictive model for urban population dynamics based on multilinear Poisson regression so as to handle multiple contexts in a systematic manner. The model is parameterized using a tensor and can be optimized by using an efficient convex optimization with a sequence of matrix parameter optimizations. An empirical evaluation with large-scale smartphone location data showed that our model outperforms conventional approaches.
Predictive Population Behavior Analysis from Multiple Contexts with Multilinear Poisson Regression（External Site Link）