Detecting Changes in Individual Travel Behavior Patterns

Although stable in the short term, individual travel behavior patterns are subject to changes in the long term. The ability to detect such changes is critical for developing behavior models that are adaptive over time. However, no sufficient method has been developed in the existing literature. The objective of this paper is to develop a methodology to detect changes in individual travel behavior patterns, which are defined as “the significant, abrupt and persistent changes in the underlying pattern of travel behavior.” To detect such changes, a distribution of travel choices is specified for three distinct dimensions of travel behavior—the frequency of travel, time of travel, and locations to visit. The authors assume that the parameters of the distribution change whenever there exits a pattern change. A Bayesian method is developed to estimate the probability that a pattern change occurs at any given time for each behavior dimension. The proposed methodology is demonstrated using pseudonymised transit smart card records of more than 3,000 individuals over two years, and the results are promising. Based on the likelihood ratio test, the behavior patterns that are partitioned by the detected changepoints are proven to improve the goodness-of-fit of the behavior model. In addition, positive correlation is found between the change probability in the temporal and spatial dimensions. The methodology presented in this paper is generalizable and can be applied to detect changes in other aspect of travel behavior and human behavior in general.

• Supplemental Notes:
  • This paper was sponsored by TRB committee ADB40 Standing Committee on Transportation Demand Forecasting.
• Authors:
  • Zhao, Zhan
  • Koutsopoulos, Haris N
  • Zhao, Jinhua
• Conference:
  • Transportation Research Board 97th Annual Meeting
  • Location: Washington DC, United States
  • Date: 2018-1-7 to 2018-1-11
• Date: 2018

Language

• English

Media Info

• Media Type: Digital/other
• Features: References;
• Pagination: 4p

Subject/Index Terms

• TRT Terms: Bayes' theorem; Behavior; Data mining; Location; Methodology; Smart cards; Time periods; Travel behavior; Travel patterns
• Uncontrolled Terms: Destinations; Travel frequency
• Subject Areas: Data and Information Technology; Planning and Forecasting; Transportation (General);

Filing Info

• Accession Number: 01659514
• Record Type: Publication
• Report/Paper Numbers: 18-00788
• Files: TRIS, TRB, ATRI
• Created Date: Feb 7 2018 1:41PM