Personalized Information Communication to Trigger Travel Choice Changes

The authors develop a personalized control system to trigger individual travel choice changes by offering personalized incentives. Individual preferences are learned to provide personalized incentives so that the promoted alternative is more likely to be accepted. The work integrates two fields (controls and human behavior) that are traditionally separate from each other: the authors model the travelers’ choice-making behaviors with the random utility theory and the data (response) from the individuals are handled by a particle filter approach for learning individual preferences. The discrete nature of travel behavior naturally leads to limited observability. The authors overcome this problem by designing a measurement function from which additional information can be solicited. Additionally, the inherent trade-off nature of travel behaviors results in an infinite set of solutions, to which two solutions are proposed: 1) the divide and conquer strategy in which a multi-dimensional conditional probability function is proposed; and 2) use of domain knowledge to restrict that preference values fall in certain ranges and are consistent with certain distributions. Simulation results show that the system is able to learn individual preferences as well as track preference changes under varying levels of noisy measurements. An online experiment involving hypothetical scenarios on departure time choices and real human beings, shows that about 65% of the recruited participants are more likely to accept the promoted alternatives given personalized incentives. The authors also showed that the changes on individual departure time can potentially lead to a significant reduction (48%) in total travel time on a simple transportation network.

  • Supplemental Notes:
    • This paper was sponsored by TRB committee ADB20 Standing Committee on Effects of Information and Communication Technologies (ICT) on Travel Choices.
  • Corporate Authors:

    Transportation Research Board

    ,    
  • Authors:
    • Zhu, Xi
    • Wang, Feilong
    • Chen, Cynthia
    • Reed, Derek D
  • Conference:
  • Date: 2019

Language

  • English

Media Info

  • Media Type: Digital/other
  • Features: Figures;
  • Pagination: 5p

Subject/Index Terms

Filing Info

  • Accession Number: 01697793
  • Record Type: Publication
  • Report/Paper Numbers: 19-05950
  • Files: TRIS, TRB, ATRI
  • Created Date: Dec 7 2018 9:37AM