Public transit offers some nice open data sets. I was searching for subway data, and found out that New York releases a large data batch of metro arrival times every morning. Not knowing much on the NYC metro, there was some research to be done, going through the metro map, route time tables, station locations and other metadata, and also some video content on the trains, driving them, and using them as a passenger.
ChatGPT assisted Python did data crunching fast, when you had the idea on what to do with the data. Leg durations, histograms, outliers, distribution fitting, train run station sequences, and so on. I didn’t run any forecasts yet, but was trying out fake data generators. One interesting idea for testing AI copilots would be simulating daily metro traffic and creating alternative sets of schedules.
