Intellectual Property India Publishes Patent Application for Machine Learning-Based Outcome-Based Education Performance Prediction And Curriculum Optimization System For Higher Education

MUMBAI, India, Sept. 28 -- Intellectual Property India has published a patent application (202641111131 A) filed by R. Swathiramya; Dr Pvs Siva Prasad; Dr M. Latha Natarajan; Dr. N. Suganthi; Dipak Mishra; Dr. Fateh Bahadur Kunwar; Rajkumar Patil; Dilip Mishra; Dr. Irissappane Dhanusu Soubache; Manu Vasudevan Unni; Dr. Dhondiram Tukaram Sakhare; and Subhash Malik on September 16, 2026, for Machine Learning-Based Outcome-Based Education Performance Prediction And Curriculum Optimization System For Higher Education.

Inventors include R. Swathiramya; Dr Pvs Siva Prasad; Dr M. Latha Natarajan; Dr. N. Suganthi; Dipak Mishra; Dr. Fateh Bahadur Kunwar; Rajkumar Patil; Dilip Mishra; Dr. Irissappane Dhanusu Soubache; Manu Vasudevan Unni; Dr. Dhondiram Tukaram Sakhare; and Subhash Malik.

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

Abstract: The present invention provides an outcome-based education (OBE) system designed for predicting performance and optimizing curricula in higher education institutions employs machine learning methods to enhance and monitor academic standards. This system features a data ingestion interface that continuously gathers both direct evaluation metrics, such as assessments and laboratory evaluations, as well as indirect metrics like stakeholder feedback, course exit surveys, and industry skill requirements. A hardware processor-controlled feature mapping engine links incoming metrics with designated Course Outcomes (COs) and Program Outcomes (POs), creating a real-time dynamic CO-PO achievement matrix. To detect potential gaps in student attainment of POs before the end of a term, a predictive machine learning engine utilizes Support Vector Machines (SVM) and Support Vector Regression (SVR), combined with hybrid optimization algorithms through cross- validation. Additionally, a closed-loop curriculum optimization engine conducts multi-criteria decision analysis on identified gaps to produce automated structural modifications to the curriculum. These modifications may include changes in topic weightings, sequencing of prerequisites, and instructional delivery methods. FIG.1

Disclaimer: Curated by HT Syndication.