MUMBAI, India, Sept. 22 -- Intellectual Property India has published a patent application (202641108981 A) filed by St. Peters Engineering College on September 10, 2026, for Intelligent Human Resource Analytics System For Employee Attrition Prediction And Retention Management.
Inventors include Mrs. Gugulothu Sravanthi, Assistant Professor In Department Of Mba, St; Mrs. Marri Shravani Rani, Assistant Professor In Department Of Mba, St Peters Engineering College, Opposite Ts Forest Academy, Kompally Road, Dullapally, Maisammaguda, Medchal, Hyderabad, Telangana; Dr. M. Nagabhaskar, Associate Professor & Hod In Department Of Mba; Dr. K. Durga Pavani, Assistant Professor In Department Of Mba, St; Mrs. M Karuna Sudha, Assistant Professor In Department Of Mba, St; and Mr. G. Pranay, Assistant Professor In Department Of Mba, St Peters Engineering College, Opposite Ts Forest Academy Kompally Road, Dullapally, Maisammaguda, Medchal, Hyderabad, Telangana.
The application for the patent was published on September 18, 2026, under issue no. 38/2026.
Abstract: The present invention discloses an Intelligent Human Resource Analytics System for Employee Attrition Prediction and Retention Management. The system is designed to help organizations identify employees who may be at risk of leaving and support HR personnel in taking timely and suitable retention measures. Conventional HR practices often depend on periodic reports, manual assessments, and general employee feedback, which may not identify potential attrition risks at an early stage. The proposed system addresses this limitation through data-driven analysis and predictive techniques. The system comprises an employee data input module, data preprocessing module, employee profile module, feature analysis module, attrition prediction module, risk assessment module, contributing factor analysis module, retention recommendation module, HR dashboard, and feedback module. The system collects relevant employee information, including performance, attendance, workload, compensation, experience, promotion history, training, job satisfaction, and other workplace factors. The collected information is processed and analyzed to identify patterns associated with employee attrition. A machine learning-based attrition prediction module generates an employee-specific attrition probability or risk score. The risk assessment module categorizes employees into suitable risk levels, such as low, medium, or high. The contributing factor analysis module identifies important factors associated with the predicted risk, while the retention recommendation module provides suitable actions based on the employee's situation. The feedback module records the results of retention actions and subsequent employee outcomes to support improvement of future predictions and recommendations. The proposed invention therefore provides an integrated and proactive approach to employee attrition prediction, risk assessment, factor identification, and personalized retention management, helping organizations make timely and informed human resource decisions.
Disclaimer: Curated by HT Syndication.
