AI-ENABLED PREDICTIVE ANALYTICS FOR EMPLOYEE WELL-BEING: A CLUSTER-BASED APPROACH TO PROACTIVE HR STRATEGIES IN THE DIGITAL ERA

In an era where digital transformation is redefining the fabric of workplaces, the emphasis on employee well-being has become central to strategic human resource management. Organizations are increasingly recognizing that the mental, emotional, and psychological wellness of employees is directly linked to productivity, innovation, retention, and overall organizational success. Traditional well-being assessment models are often reactive, relying on annual surveys and generic feedback mechanisms that fail to capture the nuances of evolving workforce needs. This paper introduces a proactive and data-driven framework using Artificial Intelligence (AI) and predictive analytics to enhance employee well-being, particularly in the dynamic environment of the Indian IT sector. The study is grounded in the application of a cluster-based segmentation model that categorizes employees into meaningful subgroups based on six core well-being dimensions: organizational culture, communication effectiveness, motivation, HR support, perception of being valued, and work-life balance. Drawing on empirical data collected from 258 IT professionals across Karnataka, the research applies K-means clustering to identify distinct well-being profiles. The optimal number of clusters was determined using the Elbow Method, resulting in the classification of respondents into High, Moderate, and Low Well-Being clusters. To statistically validate the segmentation, ANOVA tests were conducted across the six dimensions, revealing significant inter-cluster differences. Communication and organizational culture emerged as the most influential variables, with large effect sizes (Cohen’s d > 1.5), indicating their critical role in differentiating well-being levels. Chi-square tests were also performed to analyze the association between demographic variables and cluster membership, revealing significant associations particularly in relation to age group. Interestingly, younger employees (under 30) were more likely to be part of the Low Well-Being cluster, suggesting a generational shift in expectations and experiences at work. The findings highlight the utility of AI in developing personalized HR interventions that align with the unique needs of different employee segments. For instance, the High Well-Being cluster could be further engaged through leadership development and recognition programs, while the Low Well-Being group requires targeted support in communication and mental health. The cluster-based approach enables HR professionals to replace the outdated one-size-fits-all strategies with focused, data-informed practices. Beyond the empirical findings, this study contributes to the theoretical discourse on ethical AI usage in HRM. It emphasizes the need for transparency, data consent, and algorithmic fairness when deploying AI tools in people management. As AI increasingly becomes a staple in organizational decision-making, this paper advocates for a human-centric design that enhances, rather than undermines, employee welfare. In conclusion, this research offers a replicable, scalable model for integrating AI into HRM systems to support sustainable employee engagement and well-being. The methodological rigor and practical implications position this work as a valuable contribution to both academia and industry, especially as organizations prepare for future-ready, digitally empowered workforce ecosystems.