Applying gradient boosting decision trees to examine non-linear effects of the built environment on driving distance in Oslo

Abstract Although many studies have explored the relationship between the built environment and travel behavior, the literature offers limited evidence about the collective influence of built environment attributes, and their non-linear effects on travel. This study innovatively adopts gradient boosting decision trees to fill the gaps. Using data from Oslo, we apply this method to the data on both weekdays and weekends to illustrate the differential effects of built environment characteristics on driving distance. We found that they have a stronger effect on weekdays than on weekends. On weekdays, their collective influence is larger than that of demographics. Furthermore, they show salient non-linear effects on driving distance in both models, challenging the linearity assumption commonly adopted in the literature. This study also identifies effective ranges of distance to different centers and population density, and highlights the important role of sub-centers in driving reduction.

[1]  J. Friedman.  Greedy function approximation: A gradient boosting machine. , 2001 .

[2]  H. Dittmar,et al.  Location Efficiency: Neighborhood and Socio-Economic Characteristics Determine Auto Ownership and Use - Studies in Chicago, Los Angeles and San Francisco , 2002 .

[3]  N Humphrey,et al.  Driving and the built environment: the effect of compact development on motorized travel, energy use, and CO2 emissions , 2010 .

[4]  Yingling Fan,et al.  Exploring the connections among residential location, self-selection, and driving: Propensity score matching with multiple treatments , 2010 .

[5]  Petter Næss,et al.  Residential location, transport rationales and daily-life travel behaviour: The case of Hangzhou Metropolitan Area, China , 2013 .

[6]  B. Berry,et al.  Central places in Southern Germany , 1967 .

[7]  Yingling Fan,et al.  Exploring the Influences of Density on Travel Behavior Using Propensity Score Matching , 2012 .

[8]  Arvid Strand,et al.  Residential location, commuting and non-work travel in two urban areas of different size and with different center structures , 2017, Progress in Planning.

[9]  T. Gim.  The relationships between land use measures and travel behavior: a meta-analytic approach , 2013 .

[10]  Pavlos S. Kanaroglou,et al.  Urban Form and Household Activity‐Travel Behavior , 2006 .

[11]  D. Stead.  Relationships between Land Use, Socioeconomic Factors, and Travel Patterns in Britain , 2001 .

[12]  R. Ewing.  Is Los Angeles-Style Sprawl Desirable? , 1997 .

[13]  Reid Ewing,et al.  Travel and the Built Environment , 2010 .

[14]  Trevor Hastie,et al.  The Elements of Statistical Learning , 2001 .

[15]  Yanru Zhang,et al.  A gradient boosting method to improve travel time prediction , 2015 .

[16]  Yi-Shih Chung,et al.  Factor complexity of crash occurrence: An empirical demonstration using boosted regression trees. , 2013, Accident; analysis and prevention.

[17]  Reid Ewing,et al.  Travel and the Built Environment: A Synthesis , 2001 .

[18]  Lingqian Hu,et al.  Changing Effects of Job Accessibility on Employment and Commute: A Case Study of Los Angeles* , 2015 .

[19]  Tae-Hyoung Tommy Gim,et al.  A meta-analysis of the relationship between density and travel behavior , 2011, Transportation.

[20]  Petter Næss,et al.  Are Short Daily Trips Compensated by Higher Leisure Mobility? , 2006 .

[21]  Arvid Strand,et al.  Which D’s are the important ones? The effects of built environment characteristics on driving distance in Oslo and Stavanger , 2017 .

[22]  R. Cervero,et al.  TRAVEL DEMAND AND THE 3DS: DENSITY, DIVERSITY, AND DESIGN , 1997 .

[23]  R. Ewing,et al.  Growing Cooler: The Evidence on Urban Development and Climate Change , 2008 .

[24]  Petter Næss.  Residential Location, Travel, and Energy Use in the Hangzhou Metropolitan Area , 2010 .

[25]  Susan L Handy,et al.  METHODOLOGIES FOR EXPLORING THE LINK BETWEEN URBAN FORM AND TRAVEL BEHAVIOR , 1996 .

[26]  J. Scheiner,et al.  Travel Distances in Daily Travel and Long-Distance Travel: What Role is Played by Urban Form? , 2014 .

[27]  D. Brownstone,et al.  The Impact of Residential Density on Vehicle Usage and Energy Consumption , 2005 .

[28]  Li Fang,et al.  Driving and Compact Growth: A Careful Look in the Rearview Mirror , 2017 .

[29]  Deborah Salon,et al.  Heterogeneity in the relationship between the built environment and driving: Focus on neighborhood type and travel purpose , 2015 .

[30]  Petter Næss.  Accessibility, Activity Participation and Location of Activities: Exploring the Links between Residential Location and Travel Behaviour , 2006 .

[31]  Bert van Wee,et al.  Key research themes on urban space, scale, and sustainable urban mobility , 2016 .

[32]  Arvid Strand,et al.  Oslo's Farewell to Urban Sprawl , 2011 .

[33]  Mark R. Stevens,et al.  Does Compact Development Make People Drive Less? , 2017 .

[34]  Jennifer Day,et al.  Commute responses to employment decentralization: Anticipated versus actual mode choice behaviors of new town employees in Kunming, China , 2017 .

[35]  Leo Guelman,et al.  Gradient boosting trees for auto insurance loss cost modeling and prediction , 2012, Expert Syst. Appl..

[36]  P. Mokhtarian,et al.  TTB or not TTB, that is the question: a review and analysis of the empirical literature on travel time (and money) budgets , 2004 .

[37]  Reid Ewing,et al.  “Does Compact Development Make People Drive Less?” The Answer Is Yes , 2017 .

[38]  Chuan Ding,et al.  Prioritizing Influential Factors for Freeway Incident Clearance Time Prediction Using the Gradient Boosting Decision Trees Method , 2017, IEEE Transactions on Intelligent Transportation Systems.

[39]  R. Cervero,et al.  Sub-centring and Commuting: Evidence from the San Francisco Bay Area, 1980-90 , 1998 .

[40]  E. Holden,et al.  Three Challenges for the Compact City as a Sustainable Urban Form: Household Consumption of Energy and Transport in Eight Residential Areas in the Greater Oslo Region , 2005 .

[41]  Susan L Handy.  Thoughts on the Meaning of Mark Stevens’s Meta-Analysis , 2017 .

[42]  Reid Ewing,et al.  Varying influences of the built environment on household travel in 15 diverse regions of the United States , 2015 .

[43]  Xiao-shu Cao,et al.  Examining the effects of the built environment and residential self-selection on commuting trips and the related CO2 emissions: An empirical study in Guangzhou, China , 2017 .

[44]  G. De’ath.  Boosted trees for ecological modeling and prediction. , 2007, Ecology.

[45]  Chuan Ding,et al.  A gradient boosting logit model to investigate driver’s stop-or-run behavior at signalized intersections using high-resolution traffic data , 2016 .

[46]  Dibakar Saha,et al.  Prioritizing Highway Safety Manual's crash prediction variables using boosted regression trees. , 2015, Accident; analysis and prevention.

[47]  D. Chatman.  Residential Choice, the Built Environment, and Nonwork Travel: Evidence Using New Data and Methods , 2009 .

[48]  Wei-Yin Loh,et al.  Classification and regression trees , 2011, WIREs Data Mining Knowl. Discov..

[49]  J Elith,et al.  A working guide to boosted regression trees. , 2008, The Journal of animal ecology.