Modelling public transportation multi-modal route choice using smart card big data

This paper discusses the use of smart card big data to understand and evaluate the public transport network in Seoul, South Korea. Smart card data (SCD) trap multiple transit modes and cover a large population, thus providing accurate and detailed trajectory information compared with traditional survey data. The focus of this study was on understanding route choice behaviours on multi-modal routes (MMRs) by redefining the route choice problem for MMRs as a transfer subway station selection problem. The study generated accurate and realistic alternative routes by creating hyperpaths, considering overlapping bus lines and the existence of more than one bus stop around subway stations using a multinomial logit model based on 1 year of SCD. The trained models were determined to be general enough by validating them with a 6-month SCD validation set.