A Data-Driven Customer-Search Modeling With the Consideration of Traffic Environment

Abstract

In order to explore the determinants of vacant taxi drivers' customer-search behavior, this paper intends to calibrate a time-dependent Multinomial Logit (MNL) model by mining over 1.6 billion GPS records from about 8,400 taxis in Shanghai, China. First, based on the ordering points to identify the clustering structure (OPTICS) algorithm, the downtown area of Shanghai city is divided into 47 hotspots to identify the hot areas of customer delivery and searching. Then, by investigating a typical search delivery process of a vacant taxi, five candidate factors that may affect the customer-search behavior are summarized and defined. Using the maximum likelihood method, the significant factors are finally found. The results reveal that the relative passenger demand, the regional likelihood of pick-ups as well as the expected rate of return are the most significant factors influencing customer-search behavior. Although the impact of traffic situation (i.e., the en-route delay and traffic condition of the target hotspot) is not particularly significant, service providers and policymakers should still take full advantage of it to schedule taxi service and mitigate the traffic congestion caused by the circulation of vacant taxis. Besides, this paper also shows that the customer-search behavior of a vacant taxi driver varies with the time of day. Findings in this paper are expected to provide comprehensive insights about factors that should be considered in the future operation pattern of a taxi service system where human driver taxis and self-driving taxis are mixed.