Indian Railways has completed the trial of an Artificial Intelligence (AI) program to fix the waiting list for tickets. The AI-powered program has for the first time allocated vacant berths in over 200 trains in such a way that fewer people had to return without confirmed tickets. As a result, there has been a reduction in the waiting list for these trains.
The project has been in the works for the past two years, wherein the AI has been taught ticket booking data and trends over the past few years, thereby generating the right ticket combinations and reducing waiting lists.
idea train profile
The AI module has been created by Center for Railway Information Systems (CRIS), the in-house software arm of the Railways, and is called Ideal Train Profile. The AI was fed information such as how lakhs of passengers booked tickets on these trains, which origin-destination pairs were hits and flops at what time of the year, which seats remained vacant for which part of the journey, etc. ”
Why was the need felt for this?
In internal policy discussions, the Railways stated that it is not practically possible to physically increase the number of trains in each sector based on demand. But if a passenger does not get a confirmed train ticket, he/she will turn away from Indian Railways and choose other means like flights for long distance and bus for short distance. Thus the solution is to revisit your list of berths and divide them wisely.
At present the passenger is given a waiting list ticket and asked to wait for four hours before the departure. This is because a large number of berths are earmarked for different quotas of train routes and for different origin-destination combinations. But is not actually fully utilised, so the real picture becomes clear only after charting.
If a long distance train has 60 stops, there are 1,800 possible ticket combinations of origin and destination. If there are 10 stops, there are usually about 45 ticket combinations. Officials say that the potential ticket combination in Indian Railways is about one billion. The problem is most evident in night sleepers, such as the Lucknow Mail, where most people take the train to travel between Delhi and Lucknow. Other long distance trains with multiple stoppages also face this challenge.
What could happen next?
AI performs data-driven remote location selection and fully automates the process of quota distribution and suggests optimal quotas for various ticket combinations based on historical demand. The project has got the Railway Board excited about how to manage rush during peak season when the demand for confirmed tickets is at its peak. So the coming summer vacation will be the first big test for the new system.
