考虑异质性的经典随机后悔最小化模型改进研究

传统基于后悔理论的交通行为模型对异质性考虑不充分，对真实选择行为的解释存在不足.本文利用韦伯比率，考虑出行者对各方式属性变量感知的异质性，对经典随机后悔最小化模型进行改进，分别建立基于随机效用最大化，经典随机后悔最小化和改进经典随机后悔最小化的选择模型；以网约车选择行为为例进行实证研究，验证改进模型效果.结果表明：3种模型参数标定结果具有一致性，改进模型的拟合优度(0.271)和命中率(75.8%)相较于另外两个模型均较优；改进模型能更好地描述多维属性决策过程中的半补偿原则和折中效应，可以提高模型对真实选择行为的解释能力.

Improvement of Classic Random Regret Minimization Model Considering Heterogeneity

Due to the lack of consideration of heterogeneity in the traditional choice model based on regret theory, there may be errors in the interpretation of the real choice behavior. This paper uses the Weber ratio to consider the heterogeneity of travelers' perception for attribute variable to improve the classic random regret minimization model, and takes taxi- hailing choice behavior as an empirical study. Three choice models are established based on the random utility maximization, classic random regret minimization, and improved classic random regret minimization, respectively. The results suggest that the calibration results of the three models are consistent, and the improved model's goodness of fit (0.271) and hit ratio (75.8%) are both better compared with the other two models. Besides, the improved model can better describe the semi- compensation principle and compromise effect in the multidimensional attribute decision- making process. And the improved model has a strong explanatory capability to the real choice behavior.