MUMBAI, India, Sept. 14 -- Intellectual Property India has published a patent application (202641107068 A) filed by Dr. Arunkumar A; Santosh Ramdas Shivane; Dr. Ankit Dilip Patel; Dr. Ramveer; Ms. Priya Singh; Dr. S. Rasheed Mansoor Ali; Dr. T. Parimalam; and Dr. S. R. Kalaiarasi on September 05, 2026, for Employee Retention In The It Sector: A Systematic Review Of Predictive Hr Analytics Using Machine Learning.
Inventors include Dr. Arunkumar A; Santosh Ramdas Shivane; Dr. Ankit Dilip Patel; Dr. Ramveer; Ms. Priya Singh; Dr. S. Rasheed Mansoor Ali; Dr. T. Parimalam; and Dr. S. R. Kalaiarasi.
The application for the patent was published on September 11, 2026, under issue no. 37/2026.
Abstract: EMPLOYEE RETENTION IN THE IT SECTOR: A SYSTEMATIC REVIEW OF PREDICTIVE HR ANALYTICS USING MACHINE LEARNING ABSTRACT Employee retention has become a critical concern for information technology organizations because high turnover disrupts productivity, increases recruitment costs, and weakens organizational knowledge. This systematic review examines the application of predictive HR analytics and machine learning techniques for identifying employee attrition risks and supporting retention strategies in the IT sector. The study synthesizes findings from prior research on workforce datasets, predictive variables, analytical methods, model performance, and practical HR interventions. Common predictors include job satisfaction, compensation, workload, career growth, work-life balance, managerial support, tenure, performance, and employee engagement. Machine learning approaches such as logistic regression, decision trees, random forests, support vector machines, gradient boosting, and neural networks are evaluated for their ability to classify employees at risk of leaving. The review also considers challenges related to data quality, model interpretability, algorithmic bias, privacy, and ethical decision-making. Findings indicate that predictive HR analytics can strengthen evidence-based retention planning when models are transparent, regularly validated, and integrated with human judgment. The study highlights research gaps and proposes directions for developing fair, explainable, and context-sensitive retention systems for technology-driven workplaces. It further emphasizes proactive interventions that improve workforce stability, satisfaction, and organizational resilience.
Disclaimer: Curated by HT Syndication.
