Detecting pattern changes in individual travel behavior: A Bayesian approach. (June 2018)

• Record Type: Journal Article
• Authors: Zhao, Zhan; Koutsopoulos, Haris N.; Zhao, Jinhua
• Is Part Of: Transportation research. Volume 112(2018)
• Page Start: 73
• Page End: 88
• Publication Date: 2018-06
• Subjects: Pattern change detection -- Travel behavior -- Smart card data -- Bayesian inference; Transportation -- Research -- Periodicals; Transportation -- Mathematical models -- Periodicals
• DOI: 10.1016/j.trb.2018.03.017
• Languages: English
• ISSNs: 0191-2615

Abstract

Highlights: Define travel pattern change as abrupt, substantial, and persistent changes in the underlying pattern. Develop a Bayesian methodology to detect such changes in individual travel patterns. Examine travel pattern changes in three dimensions: frequency, time, and location. Compare the generalized likelihood ratio approach with the Bayesian method Identify the changepoints in travel patterns of 3, 210 users over 2 years from London. Abstract: Although stable in the short term, individual travel 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. We define travel pattern changes as "abrupt, substantial, and persistent changes in the underlying patterns of travel behavior" and develop a methodology to detect such changes in individual travel patterns. We specify one distribution for each of the three dimensions of travel behavior (the frequency of travel, time of travel, and origins/destinations), and interpret the change of the parameters of the distributions as indicating the occurrence of 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 tested using pseudonymized smart card records of 3210 users from London, U.K. over two years. The results show that the method can successfully identify significant changepoints in travel patterns. Compared to the traditional generalized likelihood ratio (GLR) approach, the Bayesian method requires less predefined parameters and is more robust. The methodology presented in this paper is generalizable and can be applied to detect changes in other aspects of travel behavior and human behavior in general.