MBTA Capstone
An attempt to improve the MBTA through Data.
Harvard Institute of Applied Computational Science


Using data to provide insight to ridership patterns.

The MBTA serves 4.8 million people throughout the Boston metro area and facilitates approximately 1.3 million trips each weekday. Aggregated entry and exit data is collected for each rail station at 15-minute intervals. Since commuting is one of the most habitual acts a metropolitan citizen performs, this data provides excellent means to predict ridership throughout the week. Even with this huge amount of data, many of the daily operational decisions have been driven by gut instinct and industry-specific knowledge.

Using data from the MBTA’s fare collection system, we found that the habitual nature of mass-transit and commuting makes it relatively easy to compute a point-estimate of consumer demand at any station at any time of day. Thus, our research focused on exploring the more nuanced aspects of how Bostonians ride the T and using the insights of the exploration to make a better prediction than simple historical models.


In order to improve the MBTA we needed to ask the right questions.
Afterall, "It is not the answer that enlightens, but the question." - Eugene Ionesco


How does weather affect ridership?


How do public events affect ridership?


What stations are similar?


Are we able to predict ridership?