Leveraging Transit Data for Behavioral Insights

The JTL-Transit Lab has worked with leading transit agencies around the world to derive unique insights into passenger behavior from transit smartcards and other automatic data collection systems. For example, we worked with Transport for London to transform 20 million daily Oyster farecard records into behavioral clusters that can inform the operation and design of the transport network. This clustering methodology has been applied to other transit agencies through long-term research collaborations. Another example of innovative research in this project is using the results of destination-inference algorithms to inform predictions of future demand.

Visit the project website.

Discovering latent activity patterns from transit smart card data

Although automatically collected human travel records can accurately capture the time and location of human movements, 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.


Dynamic Origin-Destination Prediction in Urban Rail Systems

Short-term demand predictions, typically defined as less than an hour into the future, are essential for implementing dynamic control strategies and providing useful customer information in transit applications. Knowing the expected demand enables transit operators to deploy real-time control strategies in advance of the demand surge, and minimize the impact of abnormalities on the service quality and passenger experience. One of the most useful applications of demand prediction models in transit is in predicting the congestion on station platforms and crowding on vehicles. These require information about the origin-destination (OD) demand, providing a detailed profile of how and when passengers enter and exit the service. However, existing work in the literature is limited and overwhelmingly focuses on forecasting passenger arrivals at stations. This information, while useful, is incomplete for many practical applications. We address this gap by developing a scalable methodology for real-time, short-term OD demand prediction in transit systems. Our proposed model consists of three modules: multi-resolution spatial feature extraction module for capturing the local spatial dependencies with a channel-wise attention block, auxiliary information encoding module (AIE) for encoding the exogenous information, and a module for capturing the temporal evolution of demand. The OD demand at time t, represented as a N x N matrix, is processed in two separate branches. In one branch we use the discrete wavelet transform (DWT) to decompose the demand into its different time and frequency variations, detecting patterns that are not visible in the raw data. In the other, three convolutional neural network (CNN) layers are utilized to learn the spatial dependencies from the OD demand directly. Instead of treating each channel of the resultant transformation equally, we use a squeeze-and-excitation layer to weight feature maps based on their contribution to the final prediction. A Convolutional Long Short-term Memory network (ConvLSTM) is then used to capture the temporal evolution of demand. The approach is demonstrated through a case study using 2 months of Automated Fare Collection (AFC) data from the Hong Kong Mass Transit Railway (MTR) system. The extensive evaluation of the model shows the superiority of our proposed model compared to the other compared methods.


Demand Management of Congested Public Transport Systems

Transportation demand management, long used to reduce car traffic, is receiving attention among public transport operators as a means to reduce congestion in crowded public transportation systems. Though far less studied, a more structured approach to public transport demand management (PTDM) can help agencies make informed decisions on the combination of PTDM and infrastructure investments that best manage crowding. Automated fare collection data, readily available in many public transport agencies, provide a unique platform to advance systematic approaches for the design and evaluation of PTDM strategies. The paper discusses the main steps for developing PTDM programs: (a) problem identification and formulation of program goals; (b) program design; (c) evaluation; and (d) monitoring. The problem identification phase examines bottlenecks in the system based on a spatiotemporal passenger flow analysis. The design phase identifies the main design parameters based on a categorization of potential interventions along spatial, temporal, modal, and targeted user group parameters. Evaluation takes place at the system, group, and individual levels, taking advantage of the detailed information obtained from smart card transaction data. The monitoring phase addresses the long-term sustainability of the intervention and informs potential changes to improve its effectiveness. A case study of a pre-peak fare discount policy in Hong Kong’s MTR network is used to illustrate the application of the various steps with focus on evaluation and analysis of the impacts from a behavioral point of view. Smart card data from before and after the implementation of the scheme from a panel of users was used to study policy-induced behavior shifts. A cluster analysis inferred customer groups relevant to the analysis based on their usage patterns. Users who shifted their behavior were identified based on a change point analysis and a logit model was estimated to identify the main factors that contribute to this change: the amount of time a user needed to shift his/her departure time, departure time variability, fare savings, and price sensitivity. User heterogeneity suggests that future incentives may be improved if they target specific groups.