Routines-a system for inference, analysis and prediction of users daily location visits

Abstract

Inferring user behavior patterns in their daily location visits, i.e., where people go and how long they stay there, enables a variety of useful applications such as time management systems, new location recommendations, and the opportunity for analytics. For example, digital assistants can use inferred daily patterns to automate calendar events for users, or notify users about anticipated traffic conditions to their predicted next location. Retailers, on the other hand, can use the patterns to do location-based recommendations of venues similar or in proximity of the ones anticipated to be visited. To power the above applications we built and deployed Routines-a system for inferring periodic visits to known locations about users. Association rule mining has been demonstrated in the literature to be aptly suited for interpreting user routines and for building powerful audience understanding analytics tools. Using a large, real-world dataset of users visits, we perform a wide range of experiments showcasing the performance of our system for routines inference and prediction.