The development of digital technology has encouraged organizations to utilize employee data more systematically to support talent management and performance management. Talent Analytics provides an approach for integrating various types of employee information, including competencies, performance history, feedback, employee experience, engagement, behavior, rewards, and organizational factors, to generate information that supports human resource decision-making. This study aims to analyze the application of Talent Analytics for performance prediction, identify talent indicators and predictive analytics approaches used in previous studies, and develop a conceptual framework of Talent Analytics to support employee performance prediction. This study employs a descriptive qualitative literature review approach with thematic synthesis of 17 relevant articles addressing Talent Analytics, Human Resource Analytics, employee performance, predictive analytics, machine learning, and talent management. Data were extracted based on research focus, indicators, analytical methods, technologies or models, outcomes, and key findings. The synthesis indicates that employee performance prediction can be supported through the integration of various talent indicators and the application of predictive analytics, including machine learning approaches. The literature also highlights the importance of explainability, fairness, data quality, and human involvement when predictive results are used in human resource decisions. Based on these findings, this study develops a conceptual framework linking talent data, Talent Analytics, predictive analytics, performance prediction, and decision support. The framework provides a conceptual basis for future empirical research and for developing more integrated Talent Analytics practices in employee performance management.
Copyrights © 2026