Taxi High-Income Region Recommendation and Spatial Correlation Analysis

Abstract

Taxis provide essential transport services in urban areas. In the taxi industry, the income level remains a cause of concern for taxi drivers as well as regulators. Analyzing the variation trend of taxi operation efficiency indicators throughout the day, mining high-income order hot-spots and high-income regions at different periods, will effectively improve the average hourly incomes (AHI) of drivers. This paper selects the order data for each day of holidays, working days, and non-working days through the taxi order dataset of October 2019 in Xi'an. Firstly, we analyze the variation trend of taxi operation efficiency indicators in the three days. We next divide the orders into four income levels based on the Natural Breaks accordingly. Then, we use Tyson polygon and mash map matching methods to visualize the high-income order hot-spots and high-income regions. It is significantly to analyze and summarize the visualization results. Finally, we compute the Moran'I index to measure the spatial correlation between high-income order regions and high-income regions. The results show that (1) the number and the spatial distribution of high-income order hot-spots and high-income regions at different periods are different. (2) Some places are hot-spots, but neither high-income order hot-spots nor high-income regions. (3) The high-income order regions and high-income regions have a strong correlation in spatial distribution. This study provides suggestions and insights to taxi companies and taxi drivers to increase their average hourly income (AHI) and enhance the efficiency of the taxi industry.

Spatio-temporal characteristics and influencing factors of taxi average earnings

“…With the application of big data in the transportation field, taxi GPS data is used to analyze the spatiotemporal distribution characteristics of taxi operation [2] , identify urban functional areas [3] , analyze pick-up and drop-off hotspots [4] , predicting travel demands [5] , and more. Previous studies have shown that pick-up and drop-off hotspots do not necessarily overlap with high-income order areas [6] . Therefore, to help drivers select high-earnings orders accurately, we need to analyze the spatial distribution of earnings and identify high-earnings order areas.…”

Landscape Sensitivity Assessment of Historic Districts Using a GIS-Based Method: A Case Study of Beishan Street in Hangzhou, China

“…The Thiessen polygon method for separating plots was originally used by discrete weather stations to calculate rainfall [33]. It was also used to analyze urban non-physical elements, such as real estate prices and cab fares in different areas of the city [34,35]. The assessment model in this study, which is proposed for historic districts, focuses on the history and culture of non-physical elements.…”