Intellectual Property India Publishes Patent Application for Machine Learning-Based Adaptive Tutoring System For Enhancing Student Success And Retention In Higher Education Institutions (heis)

MUMBAI, India, Sept. 28 -- Intellectual Property India has published a patent application (202621096419 A) filed by Prof. Garima Chandore; Dr. Amitkumar Ranjitbhai Pate; Dr. Shihabudheen C; Dr. Sini K; Suhana Mehar M; Mrs. K. Parimala Devi; Dr. Jahfar Sadiq P; Dr. Safvan Pt; Dr. Rajesh Mishra; S. Saheetha Banu; Dr. Nirmala Devi M; and Dr. R. K. Shukla on August 10, 2026, for Machine Learning-Based Adaptive Tutoring System For Enhancing Student Success And Retention In Higher Education Institutions (heis).

Inventors include Prof. Garima Chandore; Dr. Amitkumar Ranjitbhai Pate; Dr. Shihabudheen C; Dr. Sini K; Suhana Mehar M; Mrs. K. Parimala Devi; Dr. Jahfar Sadiq P; Dr. Safvan Pt; Dr. Rajesh Mishra; S. Saheetha Banu; Dr. Nirmala Devi M; and Dr. R. K. Shukla.

The application for the patent was published on September 25, 2026, under issue no. 39/2026.

Abstract: The present invention provides a Machine Learning-Based Adaptive Tutoring System for Enhancing Student Success and Retention in Higher Education Institutions, configured to provide personalized and continuously adaptive academic support based on student-specific learning and behavioral characteristics. The system acquires student-related data including academic performance, assessment results, attendance, assignment activity, learning interactions, engagement behavior, and historical academic information from one or more educational and institutional data sources. The acquired data is processed to generate learning and behavioral features and a dynamic student learning profile comprising competency levels, learning progress, knowledge gaps, engagement characteristics, and academic risk indicators. A machine learning prediction engine analyzes the learner profile to generate academic performance predictions and student retention risk scores, while a knowledge gap detection module identifies deficient or partially mastered concepts and prerequisite knowledge deficiencies. An adaptive tutoring engine dynamically generates a personalized tutoring pathway comprising selected learning content, tutoring activities, assessments, and difficulty levels according to the identified knowledge gaps and predicted student requirements. A personalized intervention module generates targeted academic or retention interventions when predefined risk criteria are satisfied. A feedback module evaluates subsequent student performance and interaction data to continuously update the learner profile and modify subsequent tutoring and intervention strategies, thereby providing a closed-loop adaptive tutoring mechanism for improving student learning outcomes, academic success, engagement, and retention in higher education institutions.

Disclaimer: Curated by HT Syndication.