Employee turnover continues to be one of the most critical challenges that adversely affects an organisation's performance, workforce stability, and long-term competitiveness. A high employee turnover rate increases recruitment and training costs, disrupts organisational knowledge, and negatively impacts productivity and employee morale in the work environment. Human Resource (HR) Analytics has developed as a strategic tool for identifying turnover risks and supporting evidence-based employee retention programs. This emerged as a result of the increased acceptance of data-driven decision-making. Using behavioural and organisational dimensions, this project aims to build and validate an integrated HR Analytics framework for forecasting employee turnover. Additionally, the study intends to provide successful retention methods based on the important predictors that have been identified. Using a structured questionnaire that included 52 measurement items spanning 13 latent components, primary data were obtained from 200 individuals working in manufacturing, information technology, banking, and service organisations. The research design used was a quantitative cross-sectional design. A number of statistical methods, including descriptive statistics, reliability analysis, confirmatory factor analysis (CFA), convergent and discriminant validity evaluation, and structural equation modelling (SEM), were utilised to analyse the gathered data. Based on the findings, it can be concluded that the measurement model exhibits satisfactory reliability and construct validity. The structural model reveals that employee engagement, job satisfaction, leadership support, career development, recognition, psychological safety, organisational commitment, and HR Analytics capability all positively influence employee retention. On the other hand, burnout negatively impacts retention and increases the intention to leave the organisation. The report emphasises the strategic significance of HR Analytics capacity in supporting proactive workforce management and evidence-based decision-making. The proposed framework contributes to the body of literature on human resource analytics by incorporating behavioural and organisational determinants into a comprehensive predictive model. Additionally, it provides organisations with useful insights that can be implemented to improve employee retention, decrease voluntary turnover, and enhance sustainable organisational performance through data- driven human resource management.