Identifying the factors that influence taxi demand is very important for understanding where andwhen people take taxis. This study uses a large set of GPS data from New York City (NYC) taxisalong with demographic and socioeconomic information to investigate the relationships betweentaxi demand and various other factors. A technique is developed to map the Transit Access Time(TAT), which is a measure of transit accessibility, throughout NYC‟s network to help understandthe relationship between transit accessibility and taxi demand. The taxi data is then categorizedby pick-ups and drop-offs at different times of day. A multiple linear regression model is builtfor each hour of the day for pick-ups and another model is developed for drop-offs. Weidentified six important explanatory variables that influence taxi trips including population,education, age, income, TAT, and total jobs. The influence of these factors on taxi pick-ups anddrop-offs is significant at different times of the day. It is also found that some types of jobs(which are indicators of different types of activities) are strongly associated with taxi demand atdifferent times of day, especially in Manhattan. The method applied in this study demonstratesthe temporal and spatial variation of taxi demand and the factors that determine it. These modelsshow how transit accessibility and other factors affect taxi demand, and the information is usefulfor transportation planners and policy makers to help maintain and improve the transportationsystem in a large urban network.
展开▼