Multiple routes recommendation system on massive taxi trajectories

This paper presents a cloud-based multiple-route recommendation system, xGo, that enables smartphone users to choose suitable routes based on knowledge discovered in real taxi trajectories. In modern cities, GPS-equipped taxicabs report their locations regularly, which generates a huge volume of trajectory data every day. The optimized routes can be learned by mining these massive repositories of spatio-temporal information. We propose a system that can store and manage GPS log files in a cloud-based platform, probe traffic conditions, take advantage of taxi driver route-selection intelligence, and recommend an optimal path or multiple candidates to meet customized requirements. Specifically, we leverage a Hadoop-based distributed route clustering algorithm to distinguish different routes and predict traffic conditions through the latent traffic rhythm. We evaluate our system using a real-world dataset (>100 GB) generated by about 20 000 taxis over a 2-month period in Shenzhen, China. Our experiments reveal that our service can provide appropriate routes in real time and estimate traffic conditions accurately.