An Innovative Simultaneous System of Disaggregate Models for Trip Generation, Mode, and Destination Choice

Evolution of travel demand models started from the early paper and pencil versions of conventional four-step models of the late 50s and proceeded to the activity-based models. Along this spectrum, tour-based models were developed in the transition from four-step models to activity-based models. During this transition the emphasis shifted from aggregate to disaggregate models, whereby researchers increasingly paid attention to individual decision making regarding daily activities. However, there is still a conspicuous disparity and trade-off between the practicality, precision and policy sensitivity level of the developed and proposed aggregate and disaggregate models. This disparity results in a gap in the state-of-the-art and practice of travel demand modelling which is attempted to be addressed in this paper. Unlike the conventional four-step models, a highly disaggregate travel demand modelling structure is proposed in this paper in which trip purpose, mode of transport, time of day, commute distance and destination choice decisions are modelled. All these decisions, except for the destination choice decision, are jointly modelled using the random forest method which is an advanced data mining method. Destination choice is then sequentially modelled using the same method. A serial correlation is considered among consequent trips in order to jointly model travel attributes. The proposed system of models discloses reasonable accurate results for the application developed using the 2007 household travel survey of Melbourne, Australia.

• Supplemental Notes:
  • This paper was sponsored by TRB committee ADB40 Transportation Demand Forecasting.
• Corporate Authors:

  Transportation Research Board

  500 Fifth Street, NW
  Washington, DC  United States  20001
• Authors:
  • Rashidi, Taha Hossein
  • Hasegawa, Hironobu
• Conference:
  • Transportation Research Board 93rd Annual Meeting
  • Location: Washington DC
  • Date: 2014-1-12 to 2014-1-16
• Date: 2014

Language

• English

Media Info

• Media Type: Digital/other
• Features: Figures; References; Tables;
• Pagination: 13p
• Monograph Title: TRB 93rd Annual Meeting Compendium of Papers

Subject/Index Terms

• TRT Terms: Data mining; Disaggregate analysis; Mode choice; Travel demand; Travel surveys; Trip generation
• Geographic Terms: Melbourne (Australia)
• Subject Areas: Data and Information Technology; Highways; Planning and Forecasting; I72: Traffic and Transport Planning;

Filing Info

• Accession Number: 01506608
• Record Type: Publication
• Report/Paper Numbers: 14-1080
• Files: TRIS, TRB, ATRI
• Created Date: Feb 6 2014 4:50PM