Predicting choices of street-view images: A comparison between discrete choice models and machine learning models

IF 2.8 3区 经济学 Q1 ECONOMICS Journal of Choice Modelling Pub Date : 2024-01-30 DOI:10.1016/j.jocm.2024.100470
Wei Zhu , Wei Si
{"title":"Predicting choices of street-view images: A comparison between discrete choice models and machine learning models","authors":"Wei Zhu ,&nbsp;Wei Si","doi":"10.1016/j.jocm.2024.100470","DOIUrl":null,"url":null,"abstract":"<div><p>Recently, there has been a growing interest in comparing machine learning models and Discrete Choice Models. However, no studies have been conducted on image choice problems. This study aims to fill this gap by conducting a stated preference experiment that involves choosing streets for cycling based on real-world street-view images. The choice data obtained were used to estimate and compare four models: Multinomial Logit, Mixed Logit, Deep Neural Network, and Convolutional Neural Network. Additionally, the study tested the effects of different data formats on the models' performances, including semantic interpretation, semantic segmentation, raw image, semantic map, and enriched image. The comparison focused on the models' explainability and out-of-sample predictability with new but similar choice data. The results show that (1) the Discrete Choice Models exhibit nearly equal predictability to the Deep Neural Network models, but significantly outperform the Convolutional Neural Network models; (2) the Discrete Choice Models are more explainable than the Deep Neural Network models; and (3) models trained on semantic interpretation data demonstrate better predictability than those trained on semantic segmentation data and imagery data.</p></div>","PeriodicalId":46863,"journal":{"name":"Journal of Choice Modelling","volume":"50 ","pages":"Article 100470"},"PeriodicalIF":2.8000,"publicationDate":"2024-01-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S1755534524000034/pdfft?md5=24433587821c1087e62e179a597a41b4&pid=1-s2.0-S1755534524000034-main.pdf","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Choice Modelling","FirstCategoryId":"96","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1755534524000034","RegionNum":3,"RegionCategory":"经济学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ECONOMICS","Score":null,"Total":0}
引用次数: 0

Abstract

Recently, there has been a growing interest in comparing machine learning models and Discrete Choice Models. However, no studies have been conducted on image choice problems. This study aims to fill this gap by conducting a stated preference experiment that involves choosing streets for cycling based on real-world street-view images. The choice data obtained were used to estimate and compare four models: Multinomial Logit, Mixed Logit, Deep Neural Network, and Convolutional Neural Network. Additionally, the study tested the effects of different data formats on the models' performances, including semantic interpretation, semantic segmentation, raw image, semantic map, and enriched image. The comparison focused on the models' explainability and out-of-sample predictability with new but similar choice data. The results show that (1) the Discrete Choice Models exhibit nearly equal predictability to the Deep Neural Network models, but significantly outperform the Convolutional Neural Network models; (2) the Discrete Choice Models are more explainable than the Deep Neural Network models; and (3) models trained on semantic interpretation data demonstrate better predictability than those trained on semantic segmentation data and imagery data.

查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
预测街景图像的选择:离散选择模型与机器学习模型的比较
最近,人们对机器学习模型和离散选择模型的比较越来越感兴趣。然而,目前还没有针对图像选择问题的研究。本研究旨在通过进行陈述偏好实验来填补这一空白,该实验涉及根据真实世界的街景图像选择适合骑自行车的街道。获得的选择数据被用来估计和比较四种模型:多项式 Logit、混合 Logit、深度神经网络和卷积神经网络。此外,研究还测试了不同数据格式对模型性能的影响,包括语义解释、语义分割、原始图像、语义地图和丰富图像。比较的重点是模型对新的但类似的选择数据的可解释性和样本外预测性。结果表明:(1) 离散选择模型与深度神经网络模型表现出几乎相同的可预测性,但明显优于卷积神经网络模型;(2) 离散选择模型比深度神经网络模型更具可解释性;(3) 在语义解释数据上训练的模型比在语义分割数据和图像数据上训练的模型表现出更好的可预测性。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
CiteScore
4.10
自引率
12.50%
发文量
31
期刊最新文献
Editorial Board Latent class choice models with an error structure: Investigating potential unobserved associations between latent segmentation and behavior generation Model choice and framing effects: Do discrete choice modeling decisions affect loss aversion estimates? A consistent moment equations for binary probit models with endogenous variables using instrumental variables Transformation-based flexible error structures for choice modeling
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1