Intellectual Property India Publishes Patent Application for Machine Learning-Based System For Predicting Student Academic Challenges And Enhancing Academic Performance In Higher Education

MUMBAI, India, Oct. 26 -- Intellectual Property India has published a patent application (202641123405 A) filed by Swarna Ramya P; Mohammad Manzoor Hussain; R. Portia; P. Tamilarasan; Dr. Nidhi Tiwari; Dr. K. Jhansi Rani; Sashank Sekhar Dayal; Dr. Prabakaran Paranthaman; Dr. Ruchi Bhatnagar; Ms. S. Sivaselvi; S. Peerani; and Meera Bai C on October 15, 2026, for Machine Learning-Based System For Predicting Student Academic Challenges And Enhancing Academic Performance In Higher Education.

Inventors include Swarna Ramya P; Mohammad Manzoor Hussain; R. Portia; P. Tamilarasan; Dr. Nidhi Tiwari; Dr. K. Jhansi Rani; Sashank Sekhar Dayal; Dr. Prabakaran Paranthaman; Dr. Ruchi Bhatnagar; Ms. S. Sivaselvi; S. Peerani; and Meera Bai C.

The application for the patent was published on October 23, 2026, under issue no. 43/2026.

Abstract: The present invention discloses a machine learning-based system for predicting student academic challenges and enhancing academic performance in higher education. The system obtains sanctioned academic and learning-behaviour data from varied institutional sources and executes preprocessing, temporal alignment, and feature extraction to create a unique Student Academic Challenge State Vector. An engine for predicting challenges, based on machine learning, recognizes new academic obstacles and forecasts their future development across various academic environments. A module for academic indicator contribution identifies pertinent temporal indicators linked to the anticipated challenge and produces a justification supported by evidence. An Adaptive Intervention Intelligence Engine creates and prioritizes tailored academic support strategies based on the anticipated challenge status and situational factors. A module for predicting intervention outcomes assesses the anticipated reaction prior to delivering the intervention. A monitoring module after the intervention assesses predicted and actual responses, computes prediction error, and identifies the persistence or transition of the academic issue. The system modifies the student challenge status and machine learning models based on intervention results and consistently adjusts future interventions. The invention thus offers a closed-loop computational system that combines academic challenge identification, trajectory forecasting, adaptive intervention choice, outcome prediction, and feedback-driven learning to enhance student performance in higher education. FIG.1

Disclaimer: Curated by HT Syndication.