Predicting the travel mode choice with interpretable machine learning techniques: A comparative study

R. Kohavi Wrappers for Performance Enhancement and Oblivious Decision Graphs 1995. Ahmed, 2012, The Viability of Using Automatic Vehicle Identification Data for Real-Time Crash Prediction, IEEE Trans. Intell. Transp. Syst., 13, 459, 10.1109/TITS.2011.2171052 Anas, 1981, The Estimation of Multinomial Logit Models of Joint Location and Travel Mode Choice from Aggregated Data, J. Regl. Sci., 21, 223, 10.1111/j.1467-9787.1981.tb00696.x Ashqar, 2021, Network and Station-Level Bike-Sharing System Prediction: A San Francisco Bay Area Case Study, Journal of Intelligent Transportation Systems, 1, 10.1080/15472450.2021.1948412 Assi, 2019, Travel-to-School Mode Choice Modelling Employing Artificial Intelligence Techniques: A Comparative Study, Sustainability, 11, 4484, 10.3390/su11164484 Atasoy, 2013, Attitudes towards Mode Choice in Switzerland. disP-The, Planning Review, 49, 101, 10.1080/02513625.2013.827518 Baak, 2020, A New Correlation Coefficient between Categorical, Ordinal and Interval Variables with Pearson Characteristics, Comput. Stat. Data Anal., 152, 107043, 10.1016/j.csda.2020.107043 Basso, 2018, Real-Time Crash Prediction in an Urban Expressway Using Disaggregated Data, Transportation Research Part C: Emerging Technologies, 86, 202, 10.1016/j.trc.2017.11.014 Ben-Akiva, 2018, Discrete Choice Analysis: Theory and Application to Travel Demand, Transportation Studies Bhat, 2005, A Multidimensional Mixed Ordered-Response Model for Analyzing Weekend Activity Participation, Transportation Research Part B: Methodological, 39, 255, 10.1016/j.trb.2004.04.002 Blalock, 1963, Correlated Independent Variables: The Problem of Multicollinearity, Soc. Forces, 42, 233, 10.2307/2575696 Blanchette, 2021, Influence of Weather Conditions on Children’s School Travel Mode and Physical Activity in 3 Diverse Regions of Canada, Appl. Physiol. Nutr. Metab., 46, 552, 10.1139/apnm-2020-0277 Böcker, 2016, Weather, Transport Mode Choices and Emotional Travel Experiences, Transportation Research Part A: Policy and Practice, 94, 360 Brownstone, 2000, Joint Mixed Logit Models of Stated and Revealed Preferences for Alternative-Fuel Vehicles, Transport. Res. Part B: Methodol., 34, 315, 10.1016/S0191-2615(99)00031-4 Cao, 2006, The Influences of the Built Environment and Residential Self-Selection on Pedestrian Behavior: Evidence from Austin, TX, Transportation, 33, 1, 10.1007/s11116-005-7027-2 Cervero, 2002, Built Environments and Mode Choice: Toward a Normative Framework, Transport. Res. Part D: Transp. Environ., 7, 265, 10.1016/S1361-9209(01)00024-4 Chang, 2019, Travel Mode Choice: A Data Fusion Model Using Machine Learning Methods and Evidence from Travel Diary Survey Data, Transportmet. A: Transp. Sci., 15, 1587 Chapleau, 2019, Application of Machine Learning to Two Large-Sample Household Travel Surveys: A Characterization of Travel Modes, Transp. Res. Rec., 2673, 173, 10.1177/0361198119839339 Chawla, N. V.; Japkowicz, N.; Kotcz, A. Special Issue on Learning from Imbalanced Data Sets. ACM SIGKDD Explorations Newsletter 2004. Chen, 2008, Role of the Built Environment on Mode Choice Decisions: Additional Evidence on the Impact of Density, Transportation, 35, 285, 10.1007/s11116-007-9153-5 Cheng, 2016, An Exploration of the Relationships between Socioeconomics, Land Use and Daily Trip Chain Pattern among Low-Income Residents, Transport. Plann. Technol., 39, 358, 10.1080/03081060.2016.1160579 Cheng, 2019, Structural Equation Models to Analyze Activity Participation, Trip Generation, and Mode Choice of Low-Income Commuters, Transport. Lett., 11, 341, 10.1080/19427867.2017.1364460 Cheng, 2019, Applying a Random Forest Method Approach to Model Travel Mode Choice Behavior, Travel Behav. Soc., 14, 1, 10.1016/j.tbs.2018.09.002 Daganzo, 2014 Davis, 2006, The Relationship between Precision-Recall and ROC Curves De Vos, 2016, Travel Mode Choice and Travel Satisfaction: Bridging the Gap between Decision Utility and Experienced Utility, Transportation, 43, 771, 10.1007/s11116-015-9619-9 Ding, 2016, A Gradient Boosting Logit Model to Investigate Driver’s Stop-or-Run Behavior at Signalized Intersections Using High-Resolution Traffic Data, Transport. Res. Part C: Emerg. Technol., 72, 225, 10.1016/j.trc.2016.09.016 Ding, 2017, Exploring the Influence of Built Environment on Travel Mode Choice Considering the Mediating Effects of Car Ownership and Travel Distance, Transport. Res. Part A: Pol. Pract., 100, 65 Dow, 2004, Multinomial Probit and Multinomial Logit: A Comparison of Choice Models for Voting Research, Electoral Studies, 23, 107, 10.1016/S0261-3794(03)00040-4 Du, 2019, Techniques for Interpretable Machine Learning, Commun. ACM, 63, 68, 10.1145/3359786 Eriksson, 2013, Perceived Attributes of Bus and Car Mediating Satisfaction with the Work Commute, Transport. Res. Part A: Pol. Pract., 47, 87 Ermagun, 2017, Public Transit, Active Travel, and the Journey to School: A Cross-Nested Logit Analysis, Transportmet. A: Transp. Sci., 13, 24 Ermagun, 2015, Mode Choice for School Trips: Long-Term Planning and Impact of Modal Specification on Policy Assessments, Transp. Res. Rec., 2513, 97, 10.3141/2513-12 Gao, 2019, Activity-Based Trip Chaining Behavior Analysis in the Network under the Parking Fee Scheme, Transportation, 46, 647, 10.1007/s11116-017-9809-8 Hagenauer, 2017, A Comparative Study of Machine Learning Classifiers for Modeling Travel Mode Choice, Expert Syst. Appl., 78, 273, 10.1016/j.eswa.2017.01.057 Haggar, 2019, Habit Discontinuity and Student Travel Mode Choice, Transport. Res. part F: Traff. Psychol. Behav., 64, 1, 10.1016/j.trf.2019.04.022 He, 2017, The Impact of Attitudes and Perceptions on Travel Mode Choice and Car Ownership in a Chinese Megacity: The Case of Guangzhou, Res. Transport. Econom., 62, 57, 10.1016/j.retrec.2017.03.004 Heinen, 2011, The Role of Attitudes toward Characteristics of Bicycle Commuting on the Choice to Cycle to Work over Various Distances, Transportat. Res. Part D: Transp. Environ., 16, 102, 10.1016/j.trd.2010.08.010 Hillel, 2021, A Systematic Review of Machine Learning Classification Methodologies for Modelling Passenger Mode Choice, J. Choice Model., 38, 100221, 10.1016/j.jocm.2020.100221 Horowitz, 1991, Reconsidering the Multinomial Probit Model, Transportat. Res. Part B: Methodol., 25, 433, 10.1016/0191-2615(91)90036-I Jamal, 2021, Injury Severity Prediction of Traffic Crashes with Ensemble Machine Learning Techniques: A Comparative Study, Int. J. Injury Control Saf. Promot., 28, 408, 10.1080/17457300.2021.1928233 Jianchuan, 2009, Travel Mode Choice Modeling: A Comparison of Neural Networks and Multinomial Logit Model, J. Shanghai Dianji University, 12, 323 Johnson, J.M.; Khoshgoftaar, T.M. Survey on Deep Learning with Class Imbalance. J. Big Data 2019, 6, doi:10.1186/s40537-019-0192-5. Kamargianni, 2015, Investigating the Subjective and Objective Factors Influencing Teenagers’ School Travel Mode Choice – An Integrated Choice and Latent Variable Model, Transport. Res. Part A: Pol. Pract., 78, 473 Kim, 2021, Analysis of Travel Mode Choice in Seoul Using an Interpretable Machine Learning Approach, J. Adv. Transport., 2021, 1 Koushik, 2020, Machine Learning Applications in Activity-Travel Behaviour Research: A Review, Transport reviews, 40, 288, 10.1080/01441647.2019.1704307 Lee, 2018, Comparison of Four Types of Artificial Neural Network and a Multinomial Logit Model for Travel Mode Choice Modeling, Transp. Res. Rec., 2672, 101, 10.1177/0361198118796971 Li, 2012, Population Ageing, Gender and the Transportation System, Res. Transport. Econom., 34, 39, 10.1016/j.retrec.2011.12.007 Liu, 2018, The Influence of the Built Environment on School Children’s Metro Ridership: An Exploration Using Geographically Weighted Poisson Regression Models, Sustainability, 10, 4684, 10.3390/su10124684 Liu, 2015, The Influence of Weather Characteristics Variability on Individual’s Travel Mode Choice in Different Seasons and Regions in Sweden, Transp. Policy, 41, 147, 10.1016/j.tranpol.2015.01.001 Lundberg, 2017, A Unified Approach to Interpreting Model Predictions, 4768 Ma, 2020, Nested Logit Joint Model of Travel Mode and Travel Time Choice for Urban Commuting Trips in Xi’an, China, J. Urban Plann. Dev., 146, 04020020, 10.1061/(ASCE)UP.1943-5444.0000574 Ma, 2020, Travel Mode Choice Prediction Using Deep Neural Networks With Entity Embeddings, IEEE Access, 8, 64959, 10.1109/ACCESS.2020.2985542 Macioszek, 2020, The Use of a Park and Ride System—A Case Study Based on the City of Cracow (Poland), Energies, 13, 3473, 10.3390/en13133473 Macioszek, 2020, The Bike-Sharing System as an Element of Enhancing Sustainable Mobility—A Case Study Based on a City in Poland, Sustainability, 12, 3285, 10.3390/su12083285 McFadden, 1974, The Measurement of Urban Travel Demand, J. Public Econom., 3, 303, 10.1016/0047-2727(74)90003-6 McFadden, 2000, Mixed MNL Models for Discrete Response, J. Appl. Economet., 15, 447, 10.1002/1099-1255(200009/10)15:5<447::AID-JAE570>3.0.CO;2-1 McFadden, D.; Tye, W.B.; Train, K. 1977. An Application of Diagnostic Tests for the Independence from Irrelevant Alternatives Property of the Multinomial Logit Model; Institute of Transportation Studies, University of California Berkeley, CA. Molnar, 2020, Interpretable Machine Learning, Lulu. com Morckel, 2014, The Influence of Travel Attitudes, Commute Mode Choice, and Perceived Neighborhood Characteristics on Physical Activity, J. Phys. Activ. Health, 11, 91, 10.1123/jpah.2011-0299 Omrani, 2015, Predicting Travel Mode of Individuals by Machine Learning, Transp. Res. Procedia, 10, 840, 10.1016/j.trpro.2015.09.037 Ortega, 2021, A Comprehensive Model to Study the Dynamic Accessibility of the Park & Ride System, Sustainability, 13, 4064, 10.3390/su13074064 Papola, 2004, Some Developments on the Cross-Nested Logit Model, Transport. Res. Part B: Methodol., 38, 833, 10.1016/j.trb.2003.11.001 Paulssen, 2014, Values, Attitudes and Travel Behavior: A Hierarchical Latent Variable Mixed Logit Model of Travel Mode Choice, Transportation, 41, 873, 10.1007/s11116-013-9504-3 Pinjari, 2007, Modeling Residential Sorting Effects to Understand the Impact of the Built Environment on Commute Mode Choice, Transportation, 34, 557, 10.1007/s11116-007-9127-7 Plaut, 2005, Non-Motorized Commuting in the US, Transport. Res. Part D: Transp. Environ., 10, 347, 10.1016/j.trd.2005.04.002 Ryley, 2006, Use of Non-Motorised Modes and Life Stage in Edinburgh, J. Transp. Geogr., 14, 367, 10.1016/j.jtrangeo.2005.10.001 Saito, T.; Rehmsmeier, M. The Precision-Recall Plot Is More Informative than the ROC Plot When Evaluating Binary Classifiers on Imbalanced Datasets. 2015, doi:10.1371/journal.pone.0118432. Sarkar, 2018, Effect of Perception and Attitudinal Variables on Mode Choice Behavior: A Case Study of Indian City, Agartala, Travel Behav. Soc., 12, 108, 10.1016/j.tbs.2017.04.003 Scheiner, 2007, Travel Mode Choice: Affected by Objective or Subjective Determinants?, Transportation, 34, 487, 10.1007/s11116-007-9112-1 Scheiner, 2013, A Comprehensive Study of Life Course, Cohort, and Period Effects on Changes in Travel Mode Use, Transport. Res. Part A: Pol. Pract., 47, 167 Schneider, 2013, Theory of Routine Mode Choice Decisions: An Operational Framework to Increase Sustainable Transportation, Transp. Policy, 25, 128, 10.1016/j.tranpol.2012.10.007 Schwanen, 2005, What Affects Commute Mode Choice: Neighborhood Physical Structure or Preferences toward Neighborhoods?, J. Transp. Geogr., 13, 83, 10.1016/j.jtrangeo.2004.11.001 Sekhar, 2016, Mode Choice Analysis Using Random Forrest Decision Trees, Transp. Res. Procedia, 17, 644, 10.1016/j.trpro.2016.11.119 Shanmugam, 2021, Study on Mode Choice Using Nested Logit Models in Travel towards Chennai Metropolitan City, J. Ambient Intell. Hum. Comput., 1 Shen, 2009, Latent Class Model or Mixed Logit Model? A Comparison by Transport Mode Choice Data, Appl. Econ., 41, 2915, 10.1080/00036840801964633 Soria-Lara, 2017, The Influence of Location, Socioeconomics, and Behaviour on Travel-Demand by Car in Metropolitan University Campuses, Transport. Res. Part D: Transp. Environ., 53, 149, 10.1016/j.trd.2017.04.008 Stopher, P. A Multinomial Extension of the Binary Logit Model for Choice of Mode of Travel. Northwestern University, unpublished 1969, 5. T.T.M. Thanh H.-B. Ly B.T.A. Pham Possibility of AI Application on Mode-Choice Prediction of Transport Users in Hanoi. In CIGOS, Innovation for Sustainable Infrastructure Springer 2020 2019 1179 1184. Tyrinopoulos, 2013, Factors Affecting Modal Choice in Urban Mobility, Eur. Transp. Res. Rev., 5, 27, 10.1007/s12544-012-0088-3 Ullah, 2019, Public Perception of Autonomous Car: A Case Study for Pakistan, Adv. Transp. Stud., 49 Ullah, 2021, Electric Vehicle Energy Consumption Prediction Using Stacked Generalization: An Ensemble Learning Approach, Int. J. Green Energy, 18, 896, 10.1080/15435075.2021.1881902 van den Berg, 2011, Estimating Social Travel Demand of Senior Citizens in the Netherlands, J. Transp. Geogr., 19, 323, 10.1016/j.jtrangeo.2010.03.018 Onderzoek Verplaatsingen in Nederland Relocation Survey in the Netherlands (OViN) Available online: https://www.cbs.nl/nl-nl/onze-diensten/methoden/onderzoeksomschrijvingen/korte-onderzoeksbeschrijvingen/onderzoek-verplaatsingen-in-nederland--ovin-- (accessed on 22 October 2020). Wang, S.; Mo, B.; Hess, S.; Zhao, J. Comparing Hundreds of Machine Learning Classifiers and Discrete Choice Models in Predicting Travel Behavior: An Empirical Benchmark. arXiv preprint arXiv:2102.01130 2021. Wang, 2018, Machine Learning Travel Mode Choices: Comparing the Performance of an Extreme Gradient Boosting Model with a Multinomial Logit Model, Transp. Res. Rec., 2672, 35, 10.1177/0361198118773556 Wang, 2018, Substitution Effect or Complementation Effect for Bicycle Travel Choice Preference and Other Transportation Availability: Evidence from US Large-Scale Shared Bicycle Travel Behaviour Data, J. Cleaner Prod., 194, 406, 10.1016/j.jclepro.2018.04.233 Wu, 2020, Weather, Travel Mode Choice, and Impacts on Subway Ridership in Beijing, Transport. Res. Part A: Policy Pract., 135, 264 Xiong, 2015, The Analysis of Dynamic Travel Mode Choice: A Heterogeneous Hidden Markov Approach, Transportation, 42, 985, 10.1007/s11116-015-9658-2 Xiong, 2018, A High-Order Hidden Markov Model and Its Applications for Dynamic Car Ownership Analysis, Transport. Sci., 52, 1365, 10.1287/trsc.2017.0792 Ye, 2017, Satisfaction with the Commute: The Role of Travel Mode Choice, Built Environment and Attitudes, Transport. Res. Part D: Transp. Environ., 52, 535, 10.1016/j.trd.2016.06.011 Zahid, 2020, Adopting Machine Learning and Spatial Analysis Techniques for Driver Risk Assessment: Insights from a Case Study, Int. J. Environ. Res. Public Health, 17, 1, 10.3390/ijerph17145193 Zahid, M.; Chen, Y.; Jamal, A.; Memon, Q.M. Short Term Traffic State Prediction via Hyperparameter Optimization Based Classifiers; 2020; Vol. 20; ISBN 1424-8220. Zhang, 2004, The Role of Land Use in Travel Mode Choice: Evidence from Boston and Hong Kong, J. Am. Plann. Associat., 70, 344, 10.1080/01944360408976383 Zhang, 2008, Travel Mode Choice Modeling with Support Vector Machines, Transp. Res. Rec., 2076, 141, 10.3141/2076-16 Zhang, 2017, School Travel Mode Choice in Beijing, China, J. Transp. Geograp., 62, 98, 10.1016/j.jtrangeo.2017.06.001 Zhao, 2018, Weather and Cycling: Mining Big Data to Have an in-Depth Understanding of the Association of Weather Variability with Cycling on an off-Road Trail and an on-Road Bike Lane, Transport. Res. part A: Pol. Pract., 111, 119 Zhao, 2020, Prediction and Behavioral Analysis of Travel Mode Choice: A Comparison of Machine Learning and Logit Models, Travel Behav. Soc., 20, 22, 10.1016/j.tbs.2020.02.003 Zhou, X.; Jia, X.; Du, H. July 13 2015. Travel Mode Choice Based on Perceived Quality of Bus Service. In Proceedings of the CICTP 2015; American Society of Civil Engineers: Beijing, China. pp. 1534–1545. Zhou, 2018, Mode Choice of Commuter Students in a College Town: An Exploratory Study from the United States, Sustainability, 10, 3316, 10.3390/su10093316 Cirillo, 2011, Dynamic Discrete Choice Models for Transportation, Transp. Rev., 31, 473, 10.1080/01441647.2010.533393