Customer Behavior

The Transit Lab uses expertise in travel behavior to model customer activities and provide actionable recommendations to transit agency partners. The growing availability of real-time operations and demand data enhances our ability to calibrate our models for increased accuracy. We have developed an origin-destination journey estimation process for agencies with a tap-on fare system that enables strategic and tactical decisions. Other recent behavior projects include the estimation of transfer parameters that describe customers' perception of transit transfers and evaluation of different fare products on ridership patterns.

Featured Projects

Public Transportation

Transit Assignment Under Unplanned Network Disruptions

Agency:

TFL

This research project created a dynamic passenger assignment model designed to accurately and efficiently model the impact on the Underground network of passenger behavior during unplanned disruptions. Taking into account the limited knowledge of system conditions that passengers have during disruptions allows the model to identify disruption impacts that existing models may omit.

Public Transportation

Commuter Rail Direct Marketing Experiment

Agency:

MBTA

The Transit Lab used mobile ticketing data for the MBTA commuter rail system (m-Ticket) to market monthly and weekend passes to riders. Using ridership information, the lab was able to identify riders that would be most likely to purchase a pass and sent an informational nudge. New technological developments in fare payments facilitates more direct marketing campaigns to riders who would most benefit from certain products.

Public Transportation

Personalized Customer Information and Customer Segmentation

Agency:

MTR

Information has long been recognized as an important instrument for behavioral change. However, generic information provision often proves ineffective. This project aims to develop a framework toward individualized information provision to MTR users. Effective personalization includes three components: Sparse use of information; Deep Customization; Data Infrastructure and Predictive Analytics. One methodological component is the demand prediction at the individualized customer level. The research will develop the general requirements for provision of individualized customer information, evaluate technological alternatives for the communication of information, and design potential experiments to evaluate their effectiveness. Customer segmentation will be used as the means for better understanding different passenger groups and their information needs.

Public Transportation

Passenger Assignment to Journeys

Agency:

MTR

The research is looking into the problem of assigning individual passengers to train trips. A probabilistic model utilizing detailed AFC and train movement data is under development, incorporating capacity constraints of individual vehicles. The model estimates the probability that a given passenger boarded a specific train itinerary and the probability of being denied boarding. Such a model can be used for the assessment of the capacity utilization of the system, development of detailed performance metrics from the passengers’ point of view (for example, crowding), identification of individual journey time components, and estimation of the (expected) number of passengers denied boarding, as well information that can used by travel planners.

Featured Publications

Train

Inference of Public Transportation Trip Destinations by Using Fare Transaction and Vehicle Location Data: Dynamic Programming Approach

Authors:

Gabriel E. Sanchez-Martinez

Journal:

Transportation Research Record

Date:

2017

Origin-destination matrices provide vital information for service planning, operations planning, and performance measurement of public transportation systems. In recent years, methodological advances have been made in the estimation of origin-destination matrices from disaggregate fare transaction and vehicle location data. Unlike manual origin-destination surveys, these methods provide nearly complete spatial and temporal coverage at minimal marginal cost. Early models inferred destinations on the basis of the proximity of possible destinations to the next origin and disregarded the effect of waiting time, in-vehicle time, and the number of transfers on path choice. The research reported here formulated a dynamic programming model that inferred destinations of public transportation trips on the basis of a generalized disutility minimization objective. The model inferred paths and transfers on multileg journeys and worked on systems that served a mix of gated stations and ungated stops. The model is being used to infer destinations of public transportation trips in Boston, Massachusetts, and is producing better results than could be obtained with earlier models.

Train

Mobility as a Language: Predicting Individual Mobility in Public Transportation using N-Gram Models

Authors:

Zhan Zhao, Haris N. Koutsopoulos and Jinhua Zhao

Journal:

Transportation Research Board 96th Annual Meeting

Date:

2017

For public transportation agencies, the ability to provide personalized and dynamic passenger information is crucial for improving the efficiency of demand management and enhancing customer experience. This requires understanding and especially predicting individual travel behavior in the public transportation system, which is challenging because of the heterogeneity among passengers and the variability of their behaviors. This paper presents, to the best of the authors' knowledge, the first attempt to predict individual spatiotemporal behavior of public transportation passengers using smartcard data. In this study, each trip is coded as a combination of trip start time, an entry station and an exit station. A passenger's daily mobility is represented as a chain of travel decisions. The authors propose a new modeling framework, inspired by Bayesian n-gram models used in natural language processing, to estimate the probability distribution of the next decision in the sequence. Empirical analysis using Oyster card data from London shows promising results. It is found that the exact time of travel is most challenging to predict, but the difference between the predicted time and the true value is usually small. Model performance varies greatly across individuals for the prediction of entry and particularly exit stations. Overall, the proposed model shows significant improvement over the regular n-gram models, or Markov chain-based models in general. The improvement is even larger for weekend trips when travel behavior is flexible, irregular, and considerably less predictable.

Train

Discovering Latent Activity Patterns from Transit Smart Card Data: A Spatiotemporal Topic Model

Authors:

Zhan Zhao, Haris N. Koutsopoulos and Jinhua Zhao

Journal:

Transportation Research Part C

Date:

2020

Although automatically collected human travel records can accurately capture the time and location of humanmovements, they do not directly explain the hidden semantic structures behind the data, e.g., activity types. This work proposes a probabilistic topic model, adapted from Latent Dirichlet Allocation (LDA), to discover representative and interpretable activity categorization from individual-level spatiotemporal data in an unsupervised manner. Specifically, the activity-travel episodes of an individual user are treated as words in a document, and each topic is a distribution
over space and time that corresponds to certain type of activity. The model accounts for a mixture of discrete and continuous attributes---the location, start time of day, start day of week, and duration of each activity episode. The proposed methodology is demonstrated using pseudonymized transit smart card data from London, U.K. The results show that the model can successfully distinguish the three most basic types of activities---home, work, and other. As the specified number of activity categories increases, more specific subpatterns for home and work emerge, and both the goodness of fit and predictive performance for travel behavior improve. This work makes it possible to enrich human mobility data with representative and interpretable activity patterns without relying on predefined activity categories or heuristic rules.