OpenTTC — The Pains of Predicting the Train

Last post, I’ve talked about the troubles of First & Last train arrival times, due to the lack of Subway data that the TTC neglects to publish. Now, this is an expansion on another issue that has been brought up while developing the Subway API.

Last post, I’ve talked about the troubles of tracking the First/Last train arrivals inside the TTC. Now, I’ll be going over the issues of train predictions for a chosen Subway Station.

Let’s look at Eglinton West station again; the first trains arrive at 6am and 6:22am respectfully. Now, since we know when the trains come by, we can just go by 2 minute intervals, right? Well, yes and no. The answer is yes at times, when we know that the TTC is running without any service disruptions. Now, this is Toronto. Running subway service without any service disruptions is like winning the lottery, twice, in a row. It’s near impossible.

So, what can I do? Well, actually there’s a simple solution that I can do. Instead of trying to predict something that you barely have data on, it’s better to have a property that stores any service disruption for that specific station, rather than predicting when the next train will arrive during the disruption. Why? Cause we really don’t know when the train will arrive. Yeah, there’s a disruption, but without any concrete data, we can’t assume.

Implementation shouldn’t be too hard, plus I get to learn something new!

Transit Enthusiast, and Games Enthusiast

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store