Peeking the Impact of Points of Interests on Didi
This work addresses the need for efficient car-hailing services to minimize passenger waiting times and optimize vehicle utilization, though it appears incremental as it builds on existing XGBoost methods with a POI selection scheme.
The paper tackled the problem of supply-demand estimation for online car-hailing services like Didi by analyzing the impact of points of interest (POI) categories on the supply-demand gap, resulting in more accurate and stable estimation results compared to existing methods.
Recently, the online car-hailing service, Didi, has emerged as a leader in the sharing economy. Used by passengers and drivers extensive, it becomes increasingly important for the car-hailing service providers to minimize the waiting time of passengers and optimize the vehicle utilization, thus to improve the overall user experience. Therefore, the supply-demand estimation is an indispensable ingredient of an efficient online car-hailing service. To improve the accuracy of the estimation results, we analyze the implicit relationships between the points of Interest (POI) and the supply-demand gap in this paper. The different categories of POIs have positive or negative effects on the estimation, we propose a POI selection scheme and incorporate it into XGBoost [1] to achieve more accurate estimation results. Our experiment demonstrates our method provides more accurate estimation results and more stable estimation results than the existing methods.