互联网时代出租车供需匹配及补贴方案确定

通过建立出租车供求匹配的长期和短期模型给出了打车软件平台上优化的补贴方案.长期模型中,建立出租车需求量的多元线性回归模型和供应量公式.短期模型中,应用BP神经网络预测每天高、中、低峰的出租车需求量,建立高、中、低峰供应量多元线性自回归模型.以西安市为例,在模型的基础上,通过分析实时数据得出分时段的适用于网络平台的平衡供需的补贴方案.互联网时代的补贴方案依赖于实时更新,广泛全面的大数据,更及时,多样,具有针对性,不仅有效实现了软件平台公司的盈利,也最大可能地满足了乘客,政府,由司机代表的出租车公司的需求,充分发挥了互联网在优化出租车运营方式方面的作用.

Matching Degree of Taxi Supply and Demand and Determination of Subsidy Schemes in the Internet Age

By building long and short term models of matching degree of taxi supply and demand ,an optimization of the subsidy scheme on a taxi software platform was determined .In the long term model ,a multiple linear regression model of taxi demand and a formula measuring supply were given .In the short term model ,BP Neural Network and the multiple regression model were used to measure taxi demand and supply respectively for high ,medium and low peak .Taking Xi'an as an example , through the analysis of real‐time data ,a time‐division taxi optimization subsidy scheme on Internet platform was determined . Based on timely updated ,extensive and comprehensive big data ,subsidy schemes in the Internet age are more timely varied and specific .Making full use of the Internet in optimizing taxi operation mode ,these schemes not only realize profit making of soft‐ware platform companies ,but also meet the needs of passengers ,the government and taxi companies to the greatest extent .