Evaluation and determinants of metro users' regularity: Insights from transit one-card data

Abstract

Regularity is typically defined based on the repetitive travel behavior of individuals, referring to how often travelers would utilize a specific service within a given spatio-temporal context. However, previous research on metro users' regularity primarily utilized basic metric, for example metro trip frequency, to measure regularity. What's more, metro smart card data typically encompasses time, spatial features, and card type information, lacking individual attributes such as age, gender, and type of residence, which limits in-depth analysis correlating individual attributes with travel behavior. The study obtained transit one-card data from Nanjing, China, which enabled us to extract metro user's travel and individual information. Thus, the entropy rate methodology was employed to measure metro users' regularity, while machine learning techniques were used to analyze non-linear effects of built environment, travel-related, and individual attributes on regularity. Results indicate that the built environment, travel-related, and individual attributes account for 66.66%, 33.31%, and 0.03% of the total relative importance, respectively. Two most influential variables impacting regularity, namely entertainment POIs at the origin level (17.77%) and weekdays (17.51%), belong to the built environment and travel-related attributes, respectively. In terms of individual attributes, age exhibits a greater impact on regularity compared to gender and type of residence, manifested in the variation of regularity among different age groups. This finding can assist metro policymakers in understanding metro users' travel behavior, aiming to enhance operational efficiency and optimize the user experience.