PREDICTIVE ANALYTICS FOR TALENT ACQUISITION AND RETENTION

Abstract

The growing complexity of workforce management has increased the need for analytical methods that support objective decision-making in talent acquisition and retention. This study develops a predictive framework grounded in applied mathematical modeling and machine learning principles to analyze and forecast employee recruitment success and attrition risk. The proposed approach integrates statistical classification and survival models to estimate the probability of candidate suitability and the likelihood of turnover within defined time intervals. Feature engineering techniques are employed to construct representative variables from recruitment and workforce datasets, while optimization methods are used to allocate hiring and retention resources efficiently. Simulation-based validation demonstrates that the integrated predictive model improves the accuracy of retention forecasts and reduces recruitment inefficiencies. The study contributes a quantitative foundation for human resource analytics, offering a reproducible framework for optimizing workforce planning and retention strategies through predictive modeling.