Mining Efficient Taxi Operation Strategies From Large Scale Geo-Location Data

Taxi drivers always look for strategies to locate passengers quickly and therefore increase their profit margin. In reality, the passenger seeking strategies are mostly empirical and substantially vary among taxi drivers. From the history taxi data, the top performing taxi drivers can earn 25% more than the ones with mediocre seeking strategy in the same period of time. A better strategy not only helps taxi drivers earn more with less effort, but also reduce fuel consumption and carbon emissions. It is interesting to examine the influential factors in passenger seeking strategies and find algorithms to guide taxi drivers to passenger hotspots with the right timing. With the abundant availability of history taxicab traces, the existing methods of doing taxi business have been radically changed. This paper focuses on the problem of mining efficient operation strategies from a large-scale history taxi traces collected over one year. Our approach presents generic insights into the dynamics of taxicab services with the objective of maximizing the profit margins for the concerned parties. We propose important metrics, such as trip frequency, hot spots, and taxi mileage, and provide valuable insights toward more efficient operation strategies. We analyze these metrics using techniques, such as Newton's polynomial interpolation and Gamma distribution, to understand their dynamics. Our strategies use the real taxicab traces from the city of Changsha (P.R.China), may predict the taxi rides at different times by 90.68% per day, and increase the taxi drivers income levels up to 19.38% by controlling appropriate mileage per trip and following the route across more urban hot spots.