Federated Learning Framework for Performance Insights in Cloud HR Platforms

Abstract

Cloud-based Human Resource (HR) platforms have become central to organizational decision-making, enabling continuous monitoring and evaluation of employee performance across geographically distributed environments. While these platforms provide scalability and operational efficiency, they also introduce significant concerns related to employee data privacy, regulatory compliance, and security vulnerabilities. Federated Learning (FL) has emerged as a promising paradigm that enables collaborative model training without centralizing sensitive data, making it particularly suitable for HR analytics. This paper proposes a comprehensive federated learning framework designed to extract performance insights from cloud HR systems while preserving data privacy and maintaining system resilience. The framework integrates decentralized model training, secure aggregation, and adaptive learning mechanisms tailored to heterogeneous HR data sources. Through experimental evaluation on simulated cloud HR environments, the proposed approach demonstrates improved performance prediction accuracy, reduced privacy risk, and robustness against system-level threats. The findings highlight federated learning as a viable and scalable solution for next-generation performance analytics in cloud-based HR platforms.