This study investigates the relationships between transportation expenditures and built environment (i.e., the D variables) in the United States using interpretable machine-learning (IML). Key findings include significant associations between these features, collectively contributing to 70.2 percent of feature importance. The study uncovers nonlinear relationships, such as transportation expenditures significantly declining after the compactness index value of 8. In addition, a pronounced reduction in transportation expenditures occurs when the job accessibility index falls below 4. This research contributes to (1) offering empirical evidence from nationwide analysis and (2) highlighting the potential of IML in improving our understanding, and (3) providing implications.
AlzubiJafarNayyarAnandKumarAkshi. 2018. “Machine Learning from Theory to Algorithms: An Overview.”Journal of Physics: Conference Series1142:012012. doi:10.1088/1742-6596/1142/1/012012.
4.
AmiriShamsMostafavi ShidehNarimanRusty LeeEarlHoqueSimi. 2020. “Machine Learning Approaches for Predicting Household Transportation Energy Use.”City and Environment Interactions7:100044. doi:10.1016/j.cacint.2020.100044,
5.
AnasA.1982. RESIDENTIAL LOCATION MARKETS AND URBAN TRANSPORTATION. ECONOMIC THEORY, ECONOMETRICS AND POLICY ANALYSIS WITH DISCRETE CHOICE MODELS. https://trid.trb.org/view/198673
6.
ApleyDaniel W.ZhuJingyu. 2020. “Visualizing the Effects of Predictor Variables in Black Box Supervised Learning Models.”Journal of the Royal Statistical Society: Series B (Statistical Methodology)82 (4): 1059–86. doi:10.1111/rssb.12377.
BasJavierCirilloCinziaCherchiElisabetta. 2021. “Classification of Potential Electric Vehicle Purchasers: A Machine Learning Approach.”Technological Forecasting and Social Change168:120759. doi:10.1016/j.techfore.2021.120759.
BhattUmangXiangAliceSharmaShubhamWellerAdrianTalyAnkurJiaYunhanGhoshJoydeepPuriRuchirM. F. MouraJoséEckersleyPeter. 2020. “Explainable Machine Learning in Deployment.” In Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency, 648–57. New York: Association for Computing Machinery. doi:10.1145/3351095.3375624.
11.
BiQifangGoodmanKatherine E.KaminskyJoshuaLesslerJustin. 2019. “What Is Machine Learning? A Primer for the Epidemiologist.”American Journal of Epidemiology188 (12): 2222–39. doi:10.1093/aje/kwz189.
BowesDavid R.IhlanfeldtKeith R.2001. “Identifying the Impacts of Rail Transit Stations on Residential Property Values.”Journal of Urban Economics50 (1): 1–25. doi:10.1006/juec.2001.2214.
14.
BreimanLeo. 1984. Classification and Regression Trees. New York: Routledge. doi:10.1201/9781315139470.
15.
BrisMyriamPawlakJacekPolakJohn W.2017. “How Is ICT Use Linked to Household Transport Expenditure? A Cross-National Macro Analysis of the Influence of Home Broadband Access.”Journal of Transport Geography60:231–42. doi:10.1016/j.jtrangeo.2017.03.012.
16.
BurkartNadiaHuberMarco F.2021. “A Survey on the Explainability of Supervised Machine Learning.”Journal of Artificial Intelligence Research70:245–317. doi:10.1613/jair.1.12228.
17.
CerveroRobertKockelmanKara. 1997. “Travel Demand and the 3Ds: Density, Diversity, and Design.”Transportation Research Part D: Transport and Environment2 (3): 199–219. doi:10.1016/S1361-9209(97)00009-6.
18.
ChangYung-ChiaChangKuei-HuWuGuan-Jhih. 2018. “Application of eXtreme Gradient Boosting Trees in the Construction of Credit Risk Assessment Models for Financial Institutions.”Applied Soft Computing73:914–20. doi:10.1016/j.asoc.2018.09.029.
19.
ChenTianqiGuestrinCarlos. 2016. “XGBoost: A Scalable Tree Boosting System.” In KDD ’16: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 785–94. New York: Association for Computing Machinery. doi:10.1145/2939672.2939785.
20.
ChenXingHuangLiXieDiZhaoQi. 2018. “EGBMMDA: Extreme Gradient Boosting Machine for MiRNA-Disease Association Prediction.”Cell Death & Disease9 (1): 1–16. doi:10.1038/s41419-017-0003-x.
21.
ChoiYunkyungGuhathakurtaSubhrajit. 2020. “Do People Walk More in Transit-Accessible Places?”Journal of Transport and Land Use13 (1): 343–65. doi:10.5198/jtlu.2020.1530.
22.
DingChuanCaoXinyuWangYunpeng. 2018. “Synergistic Effects of the Built Environment and Commuting Programs on Commute Mode Choice.”Transportation Research Part A: Policy and Practice118:104–18. doi:10.1016/j.tra.2018.08.041.
23.
DingChuanCaoXinyu (Jason)NæssPetter. 2018. “Applying Gradient Boosting Decision Trees to Examine Non-Linear Effects of the Built Environment on Driving Distance in Oslo.”Transportation Research Part A: Policy and Practice110:107–17. doi:10.1016/j.tra.2018.02.009.
24.
DongHongwei. 2021. “Evaluating the Impacts of Transit-Oriented Developments (TODs) on Household Transportation Expenditures in California.”Journal of Transport Geography90:102946. doi:10.1016/j.jtrangeo.2020.102946.
EwingReidCerveroRobert. 2010. “Travel and the Built Environment.”Journal of the American Planning Association76 (3): 265–94. doi:10.1080/01944361003766766.
27.
FengDe-ChengWangWen-JieMangalathuSujithTacirogluErtugrul. 2021. “Interpretable XGBoost-SHAP Machine-Learning Model for Shear Strength Prediction of Squat RC Walls.”Journal of Structural Engineering147 (11): 04021173. doi:10.1061/(ASCE)ST.1943-541X.0003115.
28.
FerdousNazneenPinjariAbdul RawoofBhatChandra R.PendyalaRam M.2010“A Comprehensive Analysis of Household Transportation Expenditures Relative to Other Goods and Services: An Application to United States Consumer Expenditure Data.”Transportation37 (3): 363–90. doi:10.1007/s11116-010-9264-2.
29.
FreitasAlex A.2014. “Comprehensible Classification Models: A Position Paper.”ACM SIGKDD Explorations Newsletter15 (1): 1–10. doi:10.1145/2594473.2594475.
30.
FriedmanJerome H.2001. “Greedy Function Approximation: A Gradient Boosting Machine.”The Annals of Statistics29 (5): 1189–232.
31.
GanningJoanna P.2017. “It’s Good but Is It Right? An Under-the-Hood View of the Location Affordability Index.”Housing Policy Debate27 (6): 807–24. doi:10.1080/10511482.2017.1312478.
32.
GhatkarJayesh GanpatSinghRakesh KumarShanmugamPalanisamy. 2019. “Classification of Algal Bloom Species from Remote Sensing Data Using an Extreme Gradient Boosted Decision Tree Model.”International Journal of Remote Sensing40 (24): 9412–38. doi:10.1080/01431161.2019.1633696.
33.
GilpinLeilani H.BauDavidYuanBen Z.BajwaAyeshaSpecterMichaelKagalLalana. 2018. “Explaining Explanations: An Overview of Interpretability of Machine Learning.” In 2018 IEEE 5th International Conference on Data Science and Advanced Analytics (DSAA), 80–89. doi:10.1109/DSAA.2018.00018.
34.
GiulianoGenevieveGordonPeterPanQishengParkJiYoung. 2010. “Accessibility and Residential Land Values: Some Tests with New Measures.”Urban Studies47:3103–30. doi:10.1177/0042098009359949.
35.
GlaeserEdward L.KohlhaseJanet E.2003. “Cities, Regions and the Decline of Transport Costs.”Papers in Regional Science83 (1): 197–228. doi:10.1007/s10110-003-0183-x.
36.
HaTran VinhAsadaTakumiArimuraMikiharu. 2019. “Determination of the Influence Factors on Household Vehicle Ownership Patterns in Phnom Penh Using Statistical and Machine Learning Methods.”Journal of Transport Geography78:70–86. doi:10.1016/j.jtrangeo.2019.05.015.
37.
HaasPeterMorseStephanieBeckerSofiaYoungLindaEslingPaul. 2013. “The Influence of Spatial and Household Characteristics on Household Transportation Costs.”Research in Transportation Business & Management, Valuing Transportation: Measuring What Matters for Sustainability7:14–26. doi:10.1016/j.rtbm.2013.03.004.
38.
HaasPeterNewmarkG. L.MorrisonT. R.2016. “Untangling Housing Cost and Transportation Interactions: The Location Affordability Index Model—Version 2 (LAIM2).”Housing Policy Debate26 (4–5): 568–82. doi:10.1080/10511482.2016.1158199.
39.
HagenauerJulianHelbichMarco. 2017. “A Comparative Study of Machine Learning Classifiers for Modeling Travel Mode Choice.”Expert Systems with Applications78:273–82. doi:10.1016/j.eswa.2017.01.057.
HuangNantianLuGuoboXuDianguo. 2016. “A Permutation Importance-Based Feature Selection Method for Short-Term Electricity Load Forecasting Using Random Forest.”Energies9 (10): 767. doi:10.3390/en9100767.
42.
JacobucciRossGrimmKevin J.2020. “Machine Learning and Psychological Research: The Unexplored Effect of Measurement.”Perspectives on Psychological Science15 (3): 809–16. doi:10.1177/1745691620902467.
43.
JiShujuanWangXinLyuTaoLiuXiaojieWangYuanqingHeinenEvaSunZhenwei. 2022. “Understanding Cycling Distance According to the Prediction of the XGBoost and the Interpretation of SHAP: A Non-Linear and Interaction Effect Analysis.”Journal of Transport Geography103:103414. doi:10.1016/j.jtrangeo.2022.103414.
KlaiberH. Allenvon HaefenRoger H.2019. “Do Random Coefficients and Alternative Specific Constants Improve Policy Analysis? An Empirical Investigation of Model Fit and Prediction.”Environmental and Resource Economics73 (1): 75–91. doi:10.1007/s10640-018-0250-z.
KrauseJosuaPererAdamNgKenney. 2016. “Interacting with Predictions: Visual Inspection of Black-Box Machine Learning Models.” In CHI ’16: Proceedings of the 2016 CHI Conference on Human Factors in Computing Systems, 5686–97. New York: Association for Computing Machinery. doi:10.1145/2858036.2858529.
48.
LeeSangwan. 2022a. “An In-Depth Understanding of the Residential Property Value Premium of a Bikesharing Service in Portland, Oregon.”Land11 (9): 1380. doi:10.3390/land11091380.
49.
LeeSangwan. 2022b. “Exploring Associations between Multimodality and Built Environment Characteristics in the U.S.”Sustainability14 (11): 6629. doi:10.3390/su14116629.
50.
LeeSangwan. 2022c. “Transportation Mode Choice Behavior in the Era of Autonomous Vehicles: The Application of Discrete Choice Modeling and Machine Learning.” Portland State University. https://pdxscholar.library.pdx.edu/open_access_etds/5995
51.
LeeSangwan. 2023. “Measuring the Influence of Transit Accessibility on Housing and Transportation Expenditures in the U.S.: A Propensity Score Matching Approach.”Case Studies on Transport Policy14:101092. doi:10.1016/j.cstp.2023.101092.
52.
LeeSangwanWangLiming. 2022. “Intermediate Effect of the COVID-19 Pandemic on Prices of Housing Near Light Rail Transit: A Case Study of the Portland Metropolitan Area.”Sustainability14 (15): 9107. doi:10.3390/su14159107.
53.
LiTiebeiDodsonJagoSipeNeil. 2015. “Differentiating Metropolitan Transport Disadvantage by Mode: Household Expenditure on Private Vehicle Fuel and Public Transport Fares in Brisbane, Australia.”Journal of Transport Geography49:16–25. doi:10.1016/j.jtrangeo.2015.10.001.
54.
LiashchynskyiPetroLiashchynskyiPavlo. 2019. “Grid Search, Random Search, Genetic Algorithm: A Big Comparison for NAS.”arXiv:1912.06059 [Cs, Stat]. http://arxiv.org/abs/1912.06059.
55.
LiuJixiangWangBoXiaoLongzhu. 2021. “Non-Linear Associations between Built Environment and Active Travel for Working and Shopping: An Extreme Gradient Boosting Approach.”Journal of Transport Geography92:103034. doi:10.1016/j.jtrangeo.2021.103034.
56.
LundbergScott M.ErionGabrielChenHughDeGraveAlexPrutkinJordan M.NairBalaKatzRonitHimmelfarbJonathanBansalNishaLeeSu-In. 2019. “Explainable AI for Trees: From Local Explanations to Global Understanding.”arXiv:1905.04610 [Cs, Stat]. http://arxiv.org/abs/1905.04610.
57.
LundbergScott M.LeeSu-In. 2017. “A Unified Approach to Interpreting Model Predictions.”arXiv:1705.07874 [Cs, Stat]. http://arxiv.org/abs/1705.07874.
58.
MakarewiczCarrieDantzlerPrentissAdkinsArlie. 2020. “Another Look at Location Affordability: Understanding the Detailed Effects of Income and Urban Form on Housing and Transportation Expenditures.”Housing Policy Debate30 (6): 1033–55. doi:10.1080/10511482.2020.1792528
59.
MercadoJoseph E.RuppMichael A.ChenJessie Y.C.BarnesMichael J.BarberDanielProcciKatelyn. 2016. “Intelligent Agent Transparency in Human–Agent Teaming for Multi-UxV Management.”Human Factors58 (3): 401–15. doi:10.1177/0018720815621206.
60.
MillerTim. 2019. “Explanation in Artificial Intelligence: Insights from the Social Sciences.”Artificial Intelligence267:1–38. doi:10.1016/j.artint.2018.07.007.
MohammadSara I.GrahamDaniel J.MeloPatricia C.AndersonRichard J.2013. “A Meta-Analysis of the Impact of Rail Projects on Land and Property Values.”Transportation Research Part A: Policy and Practice50:158–70. doi:10.1016/j.tra.2013.01.013.
MolnarChristophFreieslebenTimoKönigGunnarCasalicchioGiuseppeWrightMarvin N.BischlBernd. 2021. “Relating the Partial Dependence Plot and Permutation Feature Importance to the Data Generating Process.”arXiv:2109.01433 [Cs, Stat]. http://arxiv.org/abs/2109.01433.
65.
Mora-GarciaRaul-TomasCespedes-LopezMaria-FranciscaPerez-SanchezV. RaulMartiPabloPerez-SanchezJuan-Carlos. 2019. “Determinants of the Price of Housing in the Province of Alicante (Spain): Analysis Using Quantile Regression.”Sustainability11 (2): 437. doi:10.3390/su11020437.
66.
MurdochW. JamesSinghChandanKumbierKarlAbbasi-AslRezaYuBin. 2019. “Definitions, Methods, and Applications in Interpretable Machine Learning.”Proceedings of the National Academy of Sciences116 (44): 22071–80. doi:10.1073/pnas.1900654116.
67.
NdichuSamuelKimSangwookOzawaSeiichiBanTaoTakahashiTakeshiInoueDaisuke. 2022. “Detecting Web-Based Attacks with SHAP and Tree Ensemble Machine Learning Methods.”Applied Sciences12 (1): 60. doi:10.3390/app12010060.
68.
Poursabzi-SangdehForoughGoldsteinDaniel G.HofmanJake M.Wortman VaughanJennifer WortmanWallachHanna. 2021. “Manipulating and Measuring Model Interpretability.” In Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems, 1–52. New York: Association for Computing Machinery. doi:10.1145/3411764.3445315.
69.
RanZhi-YongHuBao-Gang. 2017. “Parameter Identifiability in Statistical Machine Learning: A Review.”Neural Computation29 (5): 1151–203. doi:10.1162/NECO_a_00947.
70.
RefaeilzadehPayamTangLeiLiuHuan. 2016. “Cross-Validation.” In Encyclopedia of Database Systems, edited by LiuLingTamer ÖzsuM., 1–7. New York: Springer. doi:10.1007/978-1-4899-7993-3_565-2.
71.
Rodríguez-PérezRaquelBajorathJürgen. 2020. “Interpretation of Machine Learning Models Using Shapley Values: Application to Compound Potency and Multi-Target Activity Predictions.”Journal of Computer-aided Molecular Design34 (10): 1013–26. doi:10.1007/s10822-020-00314-0.
72.
SchoutenAndrew. 2022. “Residential Location and Household Spending: Exploring the Relationship Between Neighborhood Characteristics and Transportation and Housing Costs.”Urban Affairs Review58 (6): 1554–84. doi:10.1177/10780874211028814.
Sidey-GibbonsJenni A. M.Sidey-GibbonsChris J.2019. “Machine Learning in Medicine: A Practical Introduction.”BMC Medical Research Methodology19 (1): 64. doi:10.1186/s12874-019-0681-4.
75.
SimeoneOsvaldo. 2018. “A Very Brief Introduction to Machine Learning With Applications to Communication Systems.”IEEE Transactions on Cognitive Communications and Networking4 (4): 648–64. doi:10.1109/TCCN.2018.2881442.
76.
SmartMichael J.KleinNicholas J.2018. “Complicating the Story of Location Affordability.”Housing Policy Debate28 (3): 393–410. doi:10.1080/10511482.2017.1371784.
77.
StroblCarolinBoulesteixAnne-LaureZeileisAchimHothornTorsten. 2007. “Bias in Random Forest Variable Importance Measures: Illustrations, Sources and a Solution.”BMC Bioinformatics8 (1): 25. doi:10.1186/1471-2105-8-25.
78.
SuShiliangWangZhuolunLiBozhaoKangMengjun. 2022. “Deciphering the Influence of TOD on Metro Ridership: An Integrated Approach of Extended Node-Place Model and Interpretable Machine Learning with Planning Implications.”Journal of Transport Geography104:103455. doi:10.1016/j.jtrangeo.2022.103455.
79.
SundararajanMukundNajmiAmir. 2020. “The Many Shapley Values for Model Explanation.” In Proceedings of the 37th International Conference on Machine Learning, 9269–78. Proceedings of Machine Learning Research. https://proceedings.mlr.press/v119/sundararajan20b.html
80.
ThakuriahPiyushimitaLiaoYihua. 2006. “Transportation Expenditures and Ability to Pay: Evidence from Consumer Expenditure Survey.”Transportation Research Record1985 (1): 257–65. doi:10.1177/0361198106198500128.
81.
TomsettRichardBrainesDaveHarborneDanPreeceAlunChakrabortySupriyo. 2018. “Interpretable to Whom? A Role-Based Model for Analyzing Interpretable Machine Learning Systems.”arXiv:1806.07552.
82.
UrryJohn. 2000. “Mobile Sociology.”The British Journal of Sociology51 (1): 185–203. doi:10.1111/j.1468-4446.2000.00185.x.
83.
van CranenburghSanderWangShenhaoVijAkshayPereiraFranciscoWalkerJoan. 2022. “Choice Modelling in the Age of Machine Learning—Discussion Paper.”Journal of Choice Modelling42:100340. doi:10.1016/j.jocm.2021.100340.
84.
VovshaPeter. 2021. “Comparison of Traditional Econometric Models and Machine Learning Methods in the Context of Travel Decision Making and Perspectives for Synergy.” In Decision Economics: Minds, Machines, and Their Society, 177–86. Studies in Computational Intelligence. Cham: Springer. doi:10.1007/978-3-030-75583-6.
85.
WangFangruRossCatherine L.2018. “Machine Learning Travel Mode Choices: Comparing the Performance of an Extreme Gradient Boosting Model with a Multinomial Logit Model.”Transportation Research Record2672 (47): 35–45. doi:10.1177/0361198118773556.
86.
XuHongwei. 2014. “Comparing Spatial and Multilevel Regression Models for Binary Outcomes in Neighborhood Studies.”Sociological Methodology44 (1): 229–72. doi:10.1177/0081175013490188.
87.
YanXiangLiuXinyuZhaoXilei. 2020. “Using Machine Learning for Direct Demand Modeling of Ridesourcing Services in Chicago.”Journal of Transport Geography83:102661. doi:10.1016/j.jtrangeo.2020.102661.
88.
YinChunCaoJasonSunBindong. 2020. “Examining Non-Linear Associations between Population Density and Waist-Hip Ratio: An Application of Gradient Boosting Decision Trees.”Cities107:102899. doi:10.1016/j.cities.2020.102899.
89.
ZhangLeiYiYimin. 2017. “Quantile House Price Indices in Beijing.”Regional Science and Urban Economics63:85–96. doi:10.1016/j.regsciurbeco.2017.01.002.
90.
ZhaoXileiYanXiangYuAlanVan HentenryckPascal. 2020. “Prediction and Behavioral Analysis of Travel Mode Choice: A Comparison of Machine Learning and Logit Models.”Travel Behaviour and Society20:22–35. doi:10.1016/j.tbs.2020.02.003.
91.
ZhouXiaoluWangMingshuLiDongying. 2019. “Bike-Sharing or Taxi? Modeling the Choices of Travel Mode in Chicago Using Machine Learning.”Journal of Transport Geography79:102479. doi:10.1016/j.jtrangeo.2019.102479.
92.
ZhouXinZolnikEdmund J.2013. “Transit-Oriented Development and Household Transportation Costs: Household-Level Analysis.”Transportation Research Record2357 (1): 86–94. doi:10.3141/2357-10.
93.
ZhouZhi-Hua. 2012. Ensemble Methods: Foundations and Algorithms. 1st ed. Boca Raton: Chapman and Hall/CRC.
