Attitudes on Autonomous Vehicle Adoption using Interpretable Gradient Boosting Machine
Attitudes on Autonomous Vehicle Adoption using Interpretable Gradient Boosting Machine
复制标题
DOI：
10.1177/0361198119857953
复制
发表时间：
2019-06
影响因子：
1.7
通讯作者：
Dongwoo Lee;John Mulrow;Chana Joanne Haboucha;S. Derrible;Y. Shiftan
中科院分区：
文献类型：
--
作者：
Dongwoo Lee;John Mulrow;Chana Joanne Haboucha;S. Derrible;Y. Shiftan
本文应用机器学习(ML)建立了与自动驾驶车辆(AV)相关的三种选择方案的选择模型：常规车辆(REG)、私人车辆(PAV)和共享车辆(SAV)。学习到的模型被用来检验用户对汽车通勤者的AV摄取的偏好和行为。具体地说，本研究将梯度助推机(GBM)应用于陈述偏好(SP)调查数据(即面板数据)。值得注意的是，与其他最大似然方法相比，广义最大似然方法具有更多的可解释特征以及对面板数据的高预测性能。通过5次交叉验证对GBM的预测性能进行了评估，结果显示准确率在80%左右。为了解释用户的行为，测量了变量重要性(VI)和部分依赖(PD)。VI的结果表明，旅行成本、购买成本和订阅成本是影响选择方案的最大变量。此外，态度变量亲AV情绪和环境关注也被显示为显著的。文章还利用所选重要因素的对数赔率的偏离度检验了选择的敏感性。研究结果为交通运输技术吸收的建模和可用于政策分析的GBM的结构和解释提供了依据。
This article applies machine learning (ML) to develop a choice model on three choice alternatives related to autonomous vehicles (AV): regular vehicle (REG), private AV (PAV), and shared AV (SAV). The learned model is used to examine users’ preferences and behaviors on AV uptake by car commuters. Specifically, this study applies gradient boosting machine (GBM) to stated preference (SP) survey data (i.e., panel data). GBM notably possesses more interpretable features than other ML methods as well as high predictive performance for panel data. The prediction performance of GBM is evaluated by conducting a 5-fold cross-validation and shows around 80% accuracy. To interpret users’ behaviors, variable importance (VI) and partial dependence (PD) were measured. The results of VI indicate that trip cost, purchase cost, and subscription cost are the most influential variables in selecting an alternative. Moreover, the attitudinal variables Pro-AV Sentiment and Environmental Concern are also shown to be significant. The article also examines the sensitivity of choice by using the PD of the log-odds on selected important factors. The results inform both the modeling of transportation technology uptake and the configuration and interpretation of GBM that can be applied for policy analysis.