Understanding commuting patterns using transit smart card data

Abstract

Commuting reflects the long-term travel behavior of people and significantly impacts urban traffic congestion and emission. Recent advances in data availability provide new opportunities to understand commuting patterns efficiently and effectively. This study develops a series of data mining methods to identify the spatiotemporal commuting patterns of Beijing public transit riders. Using one-month transit smart card data, we measure spatiotemporal regularity of individual commuters, including residence, workplace, and departure time. This data could be used to identify transit commuters by leveraging spatial clustering and multi-criteria decision analysis approaches. A disaggregated-level survey is performed to demonstrate the effectiveness of the proposed methods with a commuter identification accuracy that reaches as high as 94.1%. By visualizing the spatial distribution of the homes and workplaces of transit commuters, we determine a clear disparity between commuters and noncommuters and confirm the existence of job–house imbalance in Beijing. The findings provide useful insights for policymakers to shape a more balanced job–housing relationship by adjusting the monocentric urban structure of Beijing. In addition, the extracted individual-level commuting patterns can be used as valuable information for public transit network design and optimization. These strategies are expected to reduce car dependency, shorten excess commute, and alleviate traffic congestion.