Employee retention has become a strategic concern for commercial enterprises because avoidable turnover can increase recruitment costs, disrupt organizational knowledge, and weaken workforce continuity. This study develops an integrated decision-support framework linking artificial intelligence (AI)-enabled human resource practices, predictive analytics capability, employee data quality, AI-supported career development, organizational support for AI, employee engagement, and employee retention. The framework follows a quantitative survey design and combines descriptive statistics, reliability analysis, exploratory factor analysis, correlation, multiple regression, mediation analysis, PLS-SEM-oriented measurement assessment, and machine-learning validation. A dataset of 250 responses is used only to demonstrate the structure and presentation of statistical analysis; it is not claimed to represent actual field observations. The results indicate acceptable internal consistency, positive associations among the principal constructs, significant predictive relationships, and stronger predictive performance for nonlinear machine-learning models than the regression baseline. The study positions AI and predictive analytics not as replacements for managerial judgement but as decisionsupport mechanisms for identifying retention risks, targeting interventions, and improving evidence-based workforce planning.

Dr. V.P. Amuthanayaki,"Artificial Intelligence and Predictive Analytics in Employee Retention: A Decision Support Approach" International Journal of Advanced Multidisciplinary Research and Educational Development, V2(5): Page(802-806) September - October 2026. ISSN: 3107-6513. www.ijamred.com. Published by Scientific and Academic Research Publishing.