Peeking the Impact of Points of Interests on Didi

TL;DR

This paper improves supply-demand estimation in Didi's car-hailing service by analyzing POI impacts and integrating a POI selection scheme into XGBoost, resulting in more accurate and stable predictions.

Contribution

It introduces a POI selection scheme based on implicit relationships and incorporates it into XGBoost for enhanced estimation accuracy.

Findings

The proposed method outperforms existing approaches in accuracy.

The POI selection scheme improves estimation stability.

Different POI categories have varying effects on demand prediction.

Abstract

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.