If you live in the UK, you’ve travelled at least once with N. E. Well… If you haven’t, N.E. is a British multinational public transport company. I used to take their coaches to travel across the country. I still do. They connect all the places together by having frequent journeys to hundreds of destinations within at least the UK. So, what is this post about? Well, as I said, I am using their services mainly because of their prices. It is usually much cheaper than taking the train. However, there is one frustrating thing. Delays!! Waiting for the coaches seems never-ending. Other times you expect to go to your destination within a couple of hours and it takes four or more. It happened to me. I know, traffic. We can’t do anything about it. But, yes we can. We can at least know the schedule. We can know that the coach will actually take four hours to go to its destination and thus be prepared of the long journey.
The timetable is actually given along with the expected time to the destination…and, to my experience, it is usually wrong! So, here, I propose a simple solution that could be beneficial for both customers but also for the company.
Machine learning is a fast evolving branch lying between computer science and statistics and it could come handy. We can train intelligent algorithms to find patterns in the schedule of coaches. Specifically, we can learn their departing and arriving times and provide better estimates about each journey’s duration. So, we can know in advance that the trip is going to take more than expected or that is going to be departing late!
To the practical bit now. I believe that Gaussian Processes are ideal for this task. A periodic kernel could be used since we already know that duration depends on the day and the time of the day. Departure and arrival times can be noted down by the drivers and added to the system. Thus, a history of journeys’ times and durations can be created. Next, for any journey requested, an accurate estimation of the duration and departure time can be provided as well as the risk or the confidence interval or the uncertainty about that prediction.