Comparing and contrasting choice model and machine learning techniques in the context of vehicle ownership decisions
Comparing and contrasting choice model and machine learning techniques in the context of vehicle ownership decisions
复制标题
DOI：
10.1016/j.tra.2023.103727
复制
发表时间：
2023-07
期刊：
影响因子：
--
通讯作者：
Azam Ali;Arash Kalatian;C. Choudhury
中科院分区：
文献类型：
--
作者：
Azam Ali;Arash Kalatian;C. Choudhury
近年来，规划人员开始考虑将机器学习（ML）技术作为离散选择模型（CM）的替代方案。ML技术主要是数据驱动的，与CM相比，它通常可以实现更好的预测精度。然而，假设由于ML技术不像CMs那样具有强大的经济理论基础，因此它们可能在与“训练”场景完全不同的环境中表现不佳。还假设相对预测性能可能受到用于比较模型的度量的影响。本研究旨在通过使用2004年、2010年和2019年收集的孟加拉国达卡家庭调查数据，对车辆所有权选择进行建模，从经验上检验这两个假设。使用市场份额的对数似然和平均绝对百分比误差对CM（多项logit）和ML技术（神经网络和梯度增强树）的性能进行了比较。结果表明，对家庭收入进行分段线性变换的多项logit模型（MNL）在市场份额的对数似然和平均绝对百分比误差方面表现最佳。其次是神经网络（NN）和梯度增强树（GBT）。因此，结果提供了经验证据，证明ML技术并不总是优于CM。此外，如果预测情景有很大的不同，模型的性能差异会进一步增加。这加强了一种假设，即以行为为基础的CMs比数据驱动的ML方法更适合长期预测，特别是在人口和网络属性预计会发生重大变化的情况下。这些发现将有助于规划人员和决策者选择适当的工具来预测旅行需求。
In recent years, planners have started considering Machine Learning (ML) techniques as an alternative to discrete choice models (CM). ML techniques are primarily data-driven and typically achieve better prediction accuracy compared to CM. However, it is hypothesized that since the ML techniques do not have the strong grounding to economic theory as the CMs, they may not perform well in contexts that are radically different from the ‘training’ scenario. It is also hypothesized that the relative prediction performance may be affected by the metrics used for comparing the models.This research aims to test these two hypotheses empirically by modelling vehicle ownership choices using household survey data from Dhaka, Bangladesh collected in 2004, 2010 and 2019. The performances of CM (multinomial logit) and ML techniques (neural networks and gradient boosting trees) have been compared using log-likelihood and mean absolute percentage error of market shares.The results indicate that the multinomial logit model (MNL) with a piecewise linear transformation of the household income, has the best performance in terms of log-likelihood and mean absolute percentage error of market shares. This is followed by Neural Networks (NN) and Gradient Boosting Trees (GBT). The results thus provide empirical evidence that the ML techniques do not consistently outperform CM. Moreover, the difference in the performance of the models further increases if the prediction scenario is substantially different. This reinforces the hypothesis that CMs, with their behavioural underpinning, are better suited for long-term forecasting than data-driven ML approaches, especially if the population and network attributes are expected to change substantially. These findings will be useful for planners and policy makers in the selection of the appropriate tool for forecasting travel demand.