Project logistics
- Mentors: Dominick Tribone: dtribone@MBTA.com
- Min-max team size: 3-5
- Expected project hours per week (per team member): 6-8
- Will the project be open source? Yes Apache License
Preferred past experience
Familiarity with the following is desirable:- MS (or similar) SQL
- GTFS/GTFS-realtime (nice to have)
- Javascript/json/jquery (if interested in realtime)
- R/Matlab/Stata/SAS (stats package, basically)
- Working knowledge of statistical analysis
Overview
The MBTA sends out service alerts to inform its customers about disruptions to its rail and bus services in real-time. These alerts are usually event-driven, i.e. something happens that we believe impacts service and we send out an alert. Alerts are categorized into three groups: minor, moderate, and severe delays, but these have no strict thresholds, they are human-assigned. The MBTA is thus interested in analyzing the delay messages it has sent out and comparing it to objective measures of performance to understand the accuracy of its alerts messaging and to more quantitatively distinguish between the different levels of delays. If time allows, an additional component may be to do this type of assessment in real-time using the live MBTA alerts and performance APIs.
Some Technologies you will learn/use:
- SQL
- Statistics and stats software packages
- GTFS/GTFS-realtime (transit data spec)
- Javascript/json/jquery