Train travellers in India to benefit from a start-up’s train arrival prediction algorithm

Train travellers in India have accepted delays as part of their train journeys as inaccurate prediction leave many commuters stranded endlessly.

Big Binge Media

The Big Binge is a digital content production house dedicated to producing meaningful content that aims to inform, inspire, educate and entertain viewers.
Big Binge Media

Latest posts by Big Binge Media (see all)


New Delhi: Annoyed of train delays and inaccurate predicted time of arrival? RailYatri, a travel start-up, has been working to help train travellers in India with better predictions. The company suggests using a precision technique to predict the Estimated Time of Arrival (ETA) using machine learning based on data.

According to, train travellers in India have accepted delays as part of their train journeys. “But their frustration arises from the inability of the existing systems to correctly guide them on the ETA of trains,” the start-up said in a release.

It also said that the delays and inaccurate prediction leave many commuters stranded at platforms endlessly.

“RailYatri has innovated a unique ETA prediction algorithm using machine learning and statistical modelling techniques to predict the arrival time of running trains at their upcoming stoppage with much better precision,” it said. 

It said that the algorithm has been trained to analyse historical data of train runs spread over many years and predict the future outcome.

The start-up claimed that “its prediction is nearly 110 per cent better than the existing way of estimating train travel time.”

RailYatri Co-founder Kapil Raizada said, “The existing method to predict the ETA of trains in India have not changed over decades and is typically based on the distance divided by the speed of the train added with some buffer time for safety formula.”

“We believe that a much better technique is to make the ETA prediction based on historical data as it takes proper considerations of ground realities such as increasing traffic, rush, seasonality, etc. 

“Our ETA prediction algorithm is highly adaptive and modify themselves as it learns from subsequent inputs. Hence, the predictions get better with time,” Raizada added.

Subscribe Now: and then click on 🔔to stay updated!


Leave a reply