Traveling Path Recommendation Using Temporal Transit Patterns

Abstract

In this work, we aim to collectively recommend traveling paths by leveraging the check-in data through mining the moving behaviors of users. We call such traveling paths as Temporal Transit Patterns (TTP), which capture the representative traveling behaviors over consecutive locations, from the big check-in data. To achieve such goal, we propose a novel Temporal Transit Pattern Mining method (TTPM-method), which devises an unsupervised mechanism that automatically summarizes the representative travel patterns us guarantee better time efficiency lower and memory usage. Based on the mined TTP, a novel system, TTP-Rec, is then developed. TTP-Rec not only allows users to specify starting/end locations, but also provides the flexibility of the time constraint requirement (i.e., the expected duration of the trip). Considering a sequence of check-in points as a traveling path, we mine the frequent sequences with a ranking mechanism to achieve the goal. Our TTP-Rec targets at travelers who are unfamiliar to the objective area/city and have time limitation in the trip.