Sharing, collaborating, and benchmarking to advance travel demand research: A demonstration of short-term ridership prediction

IF 6.3 2区 工程技术 Q1 ECONOMICS
Juan D. Caicedo , Carlos Guirado , Marta C. González , Joan L. Walker
{"title":"Sharing, collaborating, and benchmarking to advance travel demand research: A demonstration of short-term ridership prediction","authors":"Juan D. Caicedo ,&nbsp;Carlos Guirado ,&nbsp;Marta C. González ,&nbsp;Joan L. Walker","doi":"10.1016/j.tranpol.2025.06.009","DOIUrl":null,"url":null,"abstract":"<div><div>This research foregrounds general practices in travel demand research, emphasizing the need to change our ways. A critical barrier preventing travel demand literature from effectively informing policy is the volume of publications without clear, consolidated benchmarks, making it difficult for researchers and policymakers to gather insights and use models to guide decision-making. By emphasizing reproducibility and open collaboration, we aim to enhance the reliability and policy relevance of travel demand research. We demonstrate this approach in the field of short-term ridership prediction. Drawing insights from over 300 studies, we develop an open-source codebase implementing five common models and propose a standardized benchmark dataset from Bogotá’s transit system, which we use to evaluate these models across stable and disruptive conditions. Our evaluation shows that online training significantly improves the prediction accuracy under demand fluctuations, with the multi-output, online-training LSTM model performing best across stable and disrupted conditions. However, even this model required approximately 1.5 months for error stabilization during the COVID-19 pandemic. The aim of this open-source codebase is to lower the barrier for other researchers to replicate models and build upon findings. We encourage researchers to test their modeling approaches on this benchmarking platform using the proposed dataset or their own, challenge our analyses, and develop model specifications that can outperform those evaluated here. Further, collaborative research approaches must be expanded across travel demand modeling if we wish to impact policy and planning.</div></div>","PeriodicalId":48378,"journal":{"name":"Transport Policy","volume":"171 ","pages":"Pages 531-541"},"PeriodicalIF":6.3000,"publicationDate":"2025-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Transport Policy","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0967070X25002343","RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ECONOMICS","Score":null,"Total":0}
引用次数: 0

Abstract

This research foregrounds general practices in travel demand research, emphasizing the need to change our ways. A critical barrier preventing travel demand literature from effectively informing policy is the volume of publications without clear, consolidated benchmarks, making it difficult for researchers and policymakers to gather insights and use models to guide decision-making. By emphasizing reproducibility and open collaboration, we aim to enhance the reliability and policy relevance of travel demand research. We demonstrate this approach in the field of short-term ridership prediction. Drawing insights from over 300 studies, we develop an open-source codebase implementing five common models and propose a standardized benchmark dataset from Bogotá’s transit system, which we use to evaluate these models across stable and disruptive conditions. Our evaluation shows that online training significantly improves the prediction accuracy under demand fluctuations, with the multi-output, online-training LSTM model performing best across stable and disrupted conditions. However, even this model required approximately 1.5 months for error stabilization during the COVID-19 pandemic. The aim of this open-source codebase is to lower the barrier for other researchers to replicate models and build upon findings. We encourage researchers to test their modeling approaches on this benchmarking platform using the proposed dataset or their own, challenge our analyses, and develop model specifications that can outperform those evaluated here. Further, collaborative research approaches must be expanded across travel demand modeling if we wish to impact policy and planning.
共享、合作和基准化以推进旅游需求研究:短期客流量预测示范
本研究展望了旅游需求研究的一般做法,强调需要改变我们的方式。阻碍旅行需求文献有效地为政策提供信息的一个关键障碍是出版物的数量没有明确、统一的基准,这使得研究人员和政策制定者难以收集见解并使用模型来指导决策。通过强调可重复性和开放式合作,我们的目标是提高旅游需求研究的可靠性和政策相关性。我们在短期客流量预测领域展示了这种方法。从300多项研究中获得见解,我们开发了一个实现五种常见模型的开源代码库,并提出了波哥大交通系统的标准化基准数据集,我们使用该数据集在稳定和破坏性条件下评估这些模型。我们的评估表明,在线训练显著提高了需求波动下的预测精度,其中多输出、在线训练的LSTM模型在稳定和中断条件下表现最好。然而,在COVID-19大流行期间,即使是这个模型也需要大约1.5个月的时间来稳定误差。这个开源代码库的目的是降低其他研究人员复制模型和构建发现的障碍。我们鼓励研究人员使用建议的数据集或他们自己的数据集在这个基准测试平台上测试他们的建模方法,挑战我们的分析,并开发可以优于此处评估的模型规范。此外,如果我们希望影响政策和规划,合作研究方法必须扩展到旅行需求建模。
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 求助全文
来源期刊
Transport Policy
Transport Policy Multiple-
CiteScore
12.10
自引率
10.30%
发文量
282
期刊介绍: Transport Policy is an international journal aimed at bridging the gap between theory and practice in transport. Its subject areas reflect the concerns of policymakers in government, industry, voluntary organisations and the public at large, providing independent, original and rigorous analysis to understand how policy decisions have been taken, monitor their effects, and suggest how they may be improved. The journal treats the transport sector comprehensively, and in the context of other sectors including energy, housing, industry and planning. All modes are covered: land, sea and air; road and rail; public and private; motorised and non-motorised; passenger and freight.
×
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
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
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 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信