As an important part of the urban traffic system, taxi makes up enormous public transportation and meets personalized travel needs. Although the ownership of private cars has surged due to augmented living conditions, the market demand for taxis is still considerable. Nowadays, there are many issues in the taxi industry, such as increasing difficulty in hailing taxis, detouring behavior, low income of employees’, which affect the healthy development of the industry, amongst which taxi drivers ’income is the key junction point of these issues. This paper establishes a Multi-layer Road Index (MRI) system for 7862 directional road segments (DRS), intending to reveal the factors affecting taxi drivers’ incomes on various road segments by mining over 4.85 million taxi trajectory GPS records within a week in Shenzhen City. Marked income differences on different directional road segments are identified, and accordingly, road segments are categorized into two income levels. Then, four categories of DRS’s factors, i.e., road attributes, traffic dynamics, point of interests (POIs) and taxi service strategies, are defined as the ones affecting income levels. We then propose a Selected-sample-based Binomial Logit (SBL) model to find the significant influencing factors. The results indicate that the road segments with different features have different income outputs over different time periods. Highly-rewarding pick-up road segments can be identified, which could contribute to drivers’ income improvements and further the healthy development of the taxi market.

CICTP