Intellectual Property India Publishes Patent Application for Ml-Based Intelligent Faculty Performance Prediction And Personalized Appraisal Recommendation System For Hrm In Higher Education Institutions

MUMBAI, India, Nov. 2 -- Intellectual Property India has published a patent application (202641124636 A) filed by Dr. G. Sindhu; R Savitha; Dr. Vetrivel. T; Dr. Santosh Kumar Nayak; Dr. R. Jeyalakshmi; Dr. Madhuchhanda Nayak; Dr. Salik Ram Dewangan; F Josephine Lenta; S. Jeyapriyanga; Shruthi. S; Devara Pavan Nagendra; and Dr. Ravindra Gharpure on October 17, 2026, for Ml-Based Intelligent Faculty Performance Prediction And Personalized Appraisal Recommendation System For Hrm In Higher Education Institutions.

Inventors include Dr. G. Sindhu; R Savitha; Dr. Vetrivel. T; Dr. Santosh Kumar Nayak; Dr. R. Jeyalakshmi; Dr. Madhuchhanda Nayak; Dr. Salik Ram Dewangan; F Josephine Lenta; S. Jeyapriyanga; Shruthi. S; Devara Pavan Nagendra; and Dr. Ravindra Gharpure.

The application for the patent was published on October 30, 2026, under issue no. 44/2026.

Abstract: ML-Based Intelligent Faculty Performance Prediction and Personalized Appraisal Recommendation System for HRM in Higher Education Institutions is the proposed invention. The proposed invention relates to an intelligent machine learning system for predicting faculty performance and generating personalized appraisal recommendations in higher education institutions. The system integrates a tabular foundation model, explainable artificial intelligence, and multi-objective optimization to evaluate heterogeneous faculty performance indicators, including teaching effectiveness, research productivity, student feedback, professional development, administrative responsibilities, and institutional contributions. A data preprocessing module transforms authorized institutional records into structured features for predictive assessment. The prediction engine estimates performance outcomes and identifies potential development requirements, while the explainability module determines the principal factors influencing individual predictions. A role-sensitive appraisal mechanism considers faculty designation, academic discipline, and workload allocation. Subsequently, a multi-objective recommendation engine generates prioritized development actions by balancing performance improvement, professional growth, workload feasibility, and institutional objectives. The system provides transparent appraisal insights through an authorized dashboard and supports human review, fairness evaluation, and privacy-conscious data processing.

Disclaimer: Curated by HT Syndication.