Custom Search

RailYatri harnesses Machine Learning to sharpen Train Delay Predictive Intelligence

Bangalore, April 11, 2018:  Travel start-up RailYatri,  has created an Estimated Arrival Time (ETA) prediction algorithm using Machine Learning and Statistical Modelling techniques to predict the arrival time of running  Indian trains at their upcoming stoppage with much better precision. The algorithm has been trained to analyse historical data of train runs spread over many years and predict the future outcome.
Figuring out and letting the passengers know when a train is going to arrive at a station is like predicting the future. Multiple variables associated with the run of a train can affect the arrival time of a train at the station and passengers are most often left waiting for hours before their train finally arrives. The result; unending anxiety of passengers, many many man hours wasted and unnecessary congestion at all the stations.
Train delays can safely be considered part and parcel of train travel in India giving the current delay trends, but what bothers the travellers most is the uncertainty around their train travel. Surveys show that while train travellers have submitted to delays being part of their travel, their frustration arises from the inability of the existing systems to correctly guide them on the estimated time of arrival (ETA) of their trains. This leaves them waiting endlessly at platforms without any idea of the exact time of arrival of their trains.
Says Kapil Raizada, Cofounder of RailYatri: “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 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.”  
RailYatri’s Smart ETA Prediction makes use of Clustering Algorithms which organizes historical train runs into thousands of patterns where time series data attributes are similar. Based on the symptoms exhibited by a running train, the ETA prediction algorithm matches through millions of permutations of patterns to make an optimized prediction in real time. As it does the forecast, the Machine Learning algorithm also determines any new running pattern which the train exhibits.  

Passengers typically check the arrival time of trains about 2-4 hrs before the start of journey and the new algorithm shows nearly 25 mins savings from unwanted wait time. This can also be a boon for Railways as they have to manage less crowd at stations with people knowing exactly when their train would be reaching the station.
RailYatri’s train ETA algorithm using Machine Learning techniques predicts nearly 110% better than the existing way of estimating train arrival time. The ETA predictions shows significant improvements even across several time frames before the actual arrival of the train. is the #1 train travel community in India. Noida-based was set up in 2011 with a mission to simplify train travel with Manish Rathi (Computer Science, Western Michigan Univ, US), Kapil Raizada (IIT Kanpur, IIM Bangalore) and Sachin Saxena (IIT Kharagpur, Stanford) as its co-founders. launched its consumer products in early 2014


Post Your Comments Now
RailYatri harnesses Machine Learning to sharpen Train Delay Predictive Intelligence
by Aly Chiman on January  29,  2019
  "Hello there, My name is Aly and I would like to know if you would have any interest to have your website here at promoted as a resource on our blog ? We are in the midst of updating our broken link resources to include current and up to date resources for our readers. Our resource links are manually approved allowing us to mark a link as a do-follow link as well . If you may be interested please in being included as a resource on our blog, please let me know. Thanks, Aly "