MUMBAI, India, Oct. 26 -- Intellectual Property India has published a patent application (202611114482 A) filed by Makemytrip India Pvt Ltd on September 24, 2026, for Method And System For Predicting A Train Seat Sell-Out Timeline.
Inventors include Sambit Sarangi; Saikiran Vajrapu; Akshita Asati; Taru Shri; Mayank Chopra; Jaideep Singh; Sumit Kumar; Dhananjay Kumar; and Shivya Gupta.
The application for the patent was published on October 23, 2026, under issue no. 43/2026.
Abstract: A method and a system for predicting a train seat sell-out timeline for a selected train journey are described. The method comprises receiving, by one or more processors, train journey search data and current train seat inventory data. A train-seat inventory key and an advance-purchase timing value are generated, and cached feature values are retrieved from a hierarchical feature cache. A sell-out prediction feature vector is generated, normalised, and supplemented with lower-specificity fallback values. A model routing unit selects a daily, hourly, low-advance-purchase, or high-advance-purchase sell-out prediction model. The selected model generates a model output vector comprising probability values for ordered sell-out buckets. The model output vector is validated and converted into a predicted days-to-sell-out bucket and value. The system generates an expected sell-out date, predicted inventory state transition, and machine-readable sell-out timeline data structure. FIG. 1
Disclaimer: Curated by HT Syndication.
