{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T01:13:13Z","timestamp":1778116393255,"version":"3.51.4"},"reference-count":56,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/100007263","name":"Virginia Polytechnic Institute and State University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100007263","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Expert Systems with Applications"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1016\/j.eswa.2026.131536","type":"journal-article","created":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T16:23:21Z","timestamp":1771950201000},"page":"131536","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Utility-informed neural networks for mode choice prediction: behaviorally constrained learning via utility gradients"],"prefix":"10.1016","volume":"316","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1985-333X","authenticated-orcid":false,"given":"Tanmay","family":"Das","sequence":"first","affiliation":[]},{"given":"Daud Nabi","family":"Hridoy","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4110-5047","authenticated-orcid":false,"given":"Md Sami","family":"Hasnine","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.eswa.2026.131536_b0005","series-title":"Theory-constrained Data-driven Model selection, Specification, and Estimation: Applications in Discrete Choice Models","author":"Aboutaleb","year":"2022"},{"key":"10.1016\/j.eswa.2026.131536_b0010","doi-asserted-by":"crossref","first-page":"88","DOI":"10.1016\/j.trpro.2025.04.012","article-title":"Modelling travel mode choice on combined data sources using machine learning methods","volume":"86","author":"Andersson","year":"2025","journal-title":"Transportation Research Procedia"},{"key":"10.1016\/j.eswa.2026.131536_b0015","doi-asserted-by":"crossref","unstructured":"Bagheri, N., Ghasri, M., & Barlow, M. H-Rum-Nn (2025): A Hybrid Neural Network Model Compatible with the Random Utility Maximisation. Available at SSRN 5101184.","DOI":"10.2139\/ssrn.5101184"},{"key":"10.1016\/j.eswa.2026.131536_b0025","unstructured":"Bailey, J. M. (1982). Comparative commuting costs: vanpooling, carpooling, and driving alone (No. HS-035 130)."},{"key":"10.1016\/j.eswa.2026.131536_b0030","unstructured":"Bay area metro: Mtc & abag. (2018), Retrieved November, 2023. https:\/\/github.com\/BayAreaMetro\/modeling-website\/wiki\/SimpleSkims."},{"key":"10.1016\/j.eswa.2026.131536_b0035","series-title":"Handbook of transportation science","first-page":"5","article-title":"Discrete choice methods and their applications to short term travel decisions","author":"Ben-Akiva","year":"1999"},{"issue":"7","key":"10.1016\/j.eswa.2026.131536_b0040","doi-asserted-by":"crossref","first-page":"455","DOI":"10.1016\/S0191-2615(98)00011-3","article-title":"Accommodating flexible substitution patterns in multi-dimensional choice modeling: Formulation and application to travel mode and departure time choice","volume":"32","author":"Bhat","year":"1998","journal-title":"Transportation Research Part B: Methodological"},{"issue":"1","key":"10.1016\/j.eswa.2026.131536_b0045","doi-asserted-by":"crossref","first-page":"287","DOI":"10.1007\/s10479-006-0015-x","article-title":"A theoretical analysis of the cross-nested logit model","volume":"144","author":"Bierlaire","year":"2006","journal-title":"Ann. Oper. Res."},{"key":"10.1016\/j.eswa.2026.131536_b0050","first-page":"738","volume":"Vol. 4, No. 4","author":"Bishop","year":"2006","journal-title":"Pattern recognition and machine learning"},{"issue":"12","key":"10.1016\/j.eswa.2026.131536_b0055","doi-asserted-by":"crossref","first-page":"1691","DOI":"10.1177\/03611981241252837","article-title":"Mode choice and value of time on long-distance vacation trips","volume":"2678","author":"Bursa","year":"2024","journal-title":"Transportation Research Record"},{"issue":"4","key":"10.1016\/j.eswa.2026.131536_b0060","doi-asserted-by":"crossref","first-page":"3795","DOI":"10.1109\/TITS.2023.3237681","article-title":"Travel mode choice prediction using imbalanced machine learning","volume":"24","author":"Chen","year":"2023","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"10.1016\/j.eswa.2026.131536_b0065","unstructured":"EIA. (2017). California all grades all formulations retail gasoline prices. Retrieved November 15, 2023, from https:\/\/www.eia.gov\/dnav\/pet\/hist\/LeafHandler.ashx?n=PET&s=EMM_EPM0_PTE_SCA_DPG&f=M."},{"key":"10.1016\/j.eswa.2026.131536_b0070","doi-asserted-by":"crossref","DOI":"10.1016\/j.trc.2024.104767","article-title":"Deep neural networks for choice analysis: Enhancing behavioral regularity with gradient regularization","volume":"166","author":"Feng","year":"2024","journal-title":"Transportation Research Part C: Emerging Technologies"},{"key":"10.1016\/j.eswa.2026.131536_b0075","doi-asserted-by":"crossref","first-page":"50","DOI":"10.1016\/j.retrec.2014.09.018","article-title":"Accounting for user type and mode effects on the value of travel time savings in project appraisal: Opportunities and challenges","volume":"47","author":"Fl\u00fcgel","year":"2014","journal-title":"Research in Transportation Economics"},{"issue":"1","key":"10.1016\/j.eswa.2026.131536_b0080","doi-asserted-by":"crossref","first-page":"117","DOI":"10.5547\/ISSN0195-6574-EJ-Vol13-No1-7","article-title":"Vehicle use and fuel economy: How big is the \u201crebound\u201d effect?","volume":"13","author":"Greene","year":"1992","journal-title":"The Energy Journal"},{"key":"10.1016\/j.eswa.2026.131536_b0085","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1016\/j.eswa.2017.01.057","article-title":"A comparative study of machine learning classifiers for modeling travel mode choice","volume":"78","author":"Hagenauer","year":"2017","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.131536_b0090","doi-asserted-by":"crossref","DOI":"10.1016\/j.trc.2025.105014","article-title":"Incorporating domain knowledge in deep neural networks for discrete choice models","volume":"171","author":"Haj-Yahia","year":"2025","journal-title":"Transportation Research Part C: Emerging Technologies"},{"key":"10.1016\/j.eswa.2026.131536_b0095","doi-asserted-by":"crossref","first-page":"166","DOI":"10.1016\/j.trb.2022.07.001","article-title":"A neural-embedded discrete choice model: Learning taste representation with strengthened interpretability","volume":"163","author":"Han","year":"2022","journal-title":"Transportation Research Part B: Methodological"},{"key":"10.1016\/j.eswa.2026.131536_b0100","doi-asserted-by":"crossref","first-page":"70","DOI":"10.1016\/j.tranpol.2018.07.011","article-title":"What about the dynamics in daily travel mode choices? a dynamic discrete choice approach for tour-based mode choice modelling","volume":"71","author":"Hasnine","year":"2018","journal-title":"Transport policy"},{"key":"10.1016\/j.eswa.2026.131536_b0105","doi-asserted-by":"crossref","first-page":"161","DOI":"10.1016\/j.jtrangeo.2018.06.003","article-title":"Determinants of travel mode choices of post-secondary students in a large metropolitan area: The case of the city of Toronto","volume":"70","author":"Hasnine","year":"2018","journal-title":"Journal of transport geography"},{"key":"10.1016\/j.eswa.2026.131536_b0110","doi-asserted-by":"crossref","first-page":"313","DOI":"10.1016\/j.jtrangeo.2018.12.007","article-title":"A random utility maximization (RUM) based measure of accessibility to transit: Accurate capturing of the first-mile issue in urban transit","volume":"74","author":"Hasnine","year":"2019","journal-title":"Journal of Transport Geography"},{"key":"10.1016\/j.eswa.2026.131536_b0115","doi-asserted-by":"crossref","DOI":"10.1016\/j.jocm.2020.100221","article-title":"A systematic review of machine learning classification methodologies for modelling passenger mode choice","volume":"38","author":"Hillel","year":"2021","journal-title":"Journal of choice modelling"},{"key":"10.1016\/j.eswa.2026.131536_b0120","first-page":"638","article-title":"Investigating preference heterogeneity in Value of Time (VOT) and Value of Reliability (VOR) estimation for managed lanes","volume":"94","author":"Hossan","year":"2016","journal-title":"Transportation Research Part A: Policy and Practice"},{"key":"10.1016\/j.eswa.2026.131536_b0125","doi-asserted-by":"crossref","first-page":"238","DOI":"10.4337\/9781839105746.00020","article-title":"Travel behaviour research in the age of machine learning: Opportunities and challenges","author":"Kalatian","year":"2024","journal-title":"Handbook of Travel Behaviour"},{"key":"10.1016\/j.eswa.2026.131536_b0130","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1016\/j.tbs.2022.07.003","article-title":"Predicting the travel mode choice with interpretable machine learning techniques: A comparative study","volume":"29","author":"Kashifi","year":"2022","journal-title":"Travel Behaviour and Society"},{"issue":"1","key":"10.1016\/j.eswa.2026.131536_b0135","article-title":"Analysis of travel mode choice in Seoul using an interpretable machine learning approach","volume":"2021","author":"Kim","year":"2021","journal-title":"Journal of Advanced Transportation"},{"key":"10.1016\/j.eswa.2026.131536_b0140","unstructured":"Koppelman, F. S., & Bhat, C. (2006). A self instructing course in mode choice modeling: multinomial and nested logit models."},{"issue":"2\u20133","key":"10.1016\/j.eswa.2026.131536_b0145","doi-asserted-by":"crossref","first-page":"231","DOI":"10.1016\/S1366-5545(00)00016-8","article-title":"The value of time and reliability: Measurement from a value pricing experiment","volume":"37","author":"Lam","year":"2001","journal-title":"Transportation Research Part E: Logistics and Transportation Review"},{"issue":"7553","key":"10.1016\/j.eswa.2026.131536_b0150","first-page":"436","volume":"521","author":"LeCun","year":"2015","journal-title":"Deep learning. nature"},{"key":"10.1016\/j.eswa.2026.131536_b0155","article-title":"A dynamic discrete choice modelling approach for forward-looking travel mode choices","volume":"190","author":"Leong","year":"2024","journal-title":"Transportation Research Part A: Policy and Practice"},{"issue":"1","key":"10.1016\/j.eswa.2026.131536_b0160","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1109\/18.61115","article-title":"Divergence measures based on the Shannon entropy","volume":"37","author":"Lin","year":"2002","journal-title":"IEEE Transactions on Information theory"},{"key":"10.1016\/j.eswa.2026.131536_b0165","doi-asserted-by":"crossref","first-page":"76","DOI":"10.1016\/j.tranpol.2015.06.014","article-title":"Pricing and mode choice based on nested logit model with trip-chain costs","volume":"44","author":"Lu","year":"2015","journal-title":"Transport Policy"},{"issue":"3","key":"10.1016\/j.eswa.2026.131536_b0170","first-page":"151","article-title":"Revisiting kernel logistic regression under the random utility models perspective","volume":"13","author":"Mart\u00edn-Baos","year":"2021","journal-title":"An interpretable machine-learning approach. Transportation Letters"},{"key":"10.1016\/j.eswa.2026.131536_b0175","series-title":"Economic Theory and Mathematical Economics","first-page":"105","article-title":"Conditional logit analysis of qualitative choice behavior","author":"McFadden","year":"1974"},{"key":"10.1016\/j.eswa.2026.131536_b0180","series-title":"Spatial Interaction Theory and Planning Models","first-page":"75","article-title":"Modeling the choice of residential location","author":"McFadden","year":"1978"},{"issue":"5","key":"10.1016\/j.eswa.2026.131536_b0185","doi-asserted-by":"crossref","first-page":"447","DOI":"10.1002\/1099-1255(200009\/10)15:5<447::AID-JAE570>3.0.CO;2-1","article-title":"Mixed MNL models for discrete response","volume":"15","author":"McFadden","year":"2000","journal-title":"Journal of applied Econometrics"},{"key":"10.1016\/j.eswa.2026.131536_b0190","article-title":"Modeling mode choice behavior of postsecondary students in large metropolitan area: A dynamic tour-based approach","volume":"39","author":"Meghna","year":"2025","journal-title":"Travel Behaviour and Society"},{"key":"10.1016\/j.eswa.2026.131536_b0290","doi-asserted-by":"crossref","first-page":"840","DOI":"10.1016\/j.trpro.2015.09.037","article-title":"Predicting travel mode of individuals by machine learning","volume":"10","author":"Omrani","year":"2015","journal-title":"Transportation Research Procedia"},{"issue":"2","key":"10.1016\/j.eswa.2026.131536_b0195","doi-asserted-by":"crossref","first-page":"213","DOI":"10.1016\/S0191-2615(00)00033-3","article-title":"On the development of the nested logit model","volume":"35","author":"Ort\u00fazar","year":"2001","journal-title":"Transportation Research Part B: Methodological"},{"issue":"9","key":"10.1016\/j.eswa.2026.131536_b0200","doi-asserted-by":"crossref","first-page":"833","DOI":"10.1016\/j.trb.2003.11.001","article-title":"Some developments on the cross-nested logit model","volume":"38","author":"Papola","year":"2004","journal-title":"Transportation Research Part B: Methodological"},{"key":"10.1016\/j.eswa.2026.131536_b0205","first-page":"1","article-title":"Interpretable machine learning: Fundamental principles and 10 grand challenges","volume":"16","author":"Rudin","year":"2022","journal-title":"Statistic Surveys"},{"key":"10.1016\/j.eswa.2026.131536_b0210","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2021.116253","article-title":"A systematic comparative evaluation of machine learning classifiers and discrete choice models for travel mode choice in the presence of response heterogeneity","volume":"193","author":"Salas","year":"2022","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.131536_b0215","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1016\/j.tbs.2021.05.007","article-title":"Rating the composition: Deconstructing the demand-side effects on transit use changes in California","volume":"25","author":"Schouten","year":"2021","journal-title":"Travel Behaviour and Society"},{"issue":"1","key":"10.1016\/j.eswa.2026.131536_b0220","doi-asserted-by":"crossref","first-page":"161","DOI":"10.3141\/2470-17","article-title":"Value of travel time savings: Evidence from I-85 express lanes in Atlanta","volume":"2470","author":"Sheikh","year":"2014","journal-title":"Georgia. Transportation Research Record"},{"key":"10.1016\/j.eswa.2026.131536_b0230","doi-asserted-by":"crossref","first-page":"236","DOI":"10.1016\/j.trb.2020.08.006","article-title":"Enhancing discrete choice models with representation learning","volume":"140","author":"Sifringer","year":"2020","journal-title":"Transportation Research Part B: Methodological"},{"issue":"4","key":"10.1016\/j.eswa.2026.131536_b0225","doi-asserted-by":"crossref","first-page":"1367","DOI":"10.1111\/j.1468-0262.2005.00619.x","article-title":"Uncovering the distribution of motorists' preferences for travel time and reliability","volume":"73","author":"Small","year":"2005","journal-title":"Econometrica"},{"issue":"2","key":"10.1016\/j.eswa.2026.131536_b0235","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1016\/0191-2615(87)90009-9","article-title":"Incorporating random constraints in discrete models of choice set generation","volume":"21","author":"Swait","year":"1987","journal-title":"Transportation Research Part B: Methodological"},{"key":"10.1016\/j.eswa.2026.131536_b0240","doi-asserted-by":"crossref","DOI":"10.1016\/j.jtrangeo.2023.103644","article-title":"Exploring the influences of ride-hailing services on VMT and transit usage\u2013evidence from California","volume":"110","author":"Tian","year":"2023","journal-title":"Journal of Transport Geography"},{"key":"10.1016\/j.eswa.2026.131536_b0245","series-title":"Discrete choice methods with simulation","author":"Train","year":"2009"},{"issue":"1","key":"10.1016\/j.eswa.2026.131536_b0250","doi-asserted-by":"crossref","first-page":"6","DOI":"10.3141\/1607-02","article-title":"Application of cross-nested logit model to mode choice in Tel Aviv, Israel, metropolitan area","volume":"1607","author":"Vovsha","year":"1997","journal-title":"Transportation Research Record"},{"key":"10.1016\/j.eswa.2026.131536_b0260","doi-asserted-by":"crossref","DOI":"10.1016\/j.trc.2020.102701","article-title":"Deep neural networks for choice analysis: Extracting complete economic information for interpretation","volume":"118","author":"Wang","year":"2020","journal-title":"Transportation Research Part C: Emerging Technologies"},{"key":"10.1016\/j.eswa.2026.131536_b0255","doi-asserted-by":"crossref","first-page":"234","DOI":"10.1016\/j.trc.2020.01.012","article-title":"Deep neural networks for choice analysis: Architecture design with alternative-specific utility functions","volume":"112","author":"Wang","year":"2020","journal-title":"Transportation Research Part C: Emerging Technologies"},{"issue":"7","key":"10.1016\/j.eswa.2026.131536_b0265","doi-asserted-by":"crossref","first-page":"627","DOI":"10.1016\/S0191-2615(00)00045-X","article-title":"The generalized nested logit model","volume":"35","author":"Wen","year":"2001","journal-title":"Transportation Research Part B: Methodological"},{"key":"10.1016\/j.eswa.2026.131536_b0270","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1016\/j.trd.2013.04.002","article-title":"Fuel economy, cost, and greenhouse gas results for alternative fuel vehicles in 2011","volume":"23","author":"Windecker","year":"2013","journal-title":"Transportation Research Part D: Transport and Environment"},{"issue":"4","key":"10.1016\/j.eswa.2026.131536_b0275","doi-asserted-by":"crossref","first-page":"433","DOI":"10.1139\/l11-015","article-title":"Commuting mode choice in the context of travel demand management (TDM) policies: An empirical investigation in Edmonton","volume":"38","author":"Zaman","year":"2011","journal-title":"Alberta. Canadian Journal of Civil Engineering"},{"key":"10.1016\/j.eswa.2026.131536_b0280","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1016\/j.tbs.2020.02.003","article-title":"Prediction and behavioral analysis of travel mode choice: A comparison of machine learning and logit models","volume":"20","author":"Zhao","year":"2020","journal-title":"Travel behaviour and society"}],"container-title":["Expert Systems with Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426004495?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426004495?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T00:42:43Z","timestamp":1778114563000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0957417426004495"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":56,"alternative-id":["S0957417426004495"],"URL":"https:\/\/doi.org\/10.1016\/j.eswa.2026.131536","relation":{},"ISSN":["0957-4174"],"issn-type":[{"value":"0957-4174","type":"print"}],"subject":[],"published":{"date-parts":[[2026,6]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Utility-informed neural networks for mode choice prediction: behaviorally constrained learning via utility gradients","name":"articletitle","label":"Article Title"},{"value":"Expert Systems with Applications","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.eswa.2026.131536","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"131536"}}