Privacy-Aware Performance Evaluation in Cloud HR Platforms Using Federated Learning

Abstract

In the era of digital transformation, Human Resource (HR) platforms increasingly rely on cloud computing to process and analyze vast amounts of employee performance data. While cloud-based systems offer scalability and accessibility, concerns regarding data privacy and regulatory compliance remain significant. This paper proposes a privacy-aware framework for performance evaluation in cloud HR platforms using Federated Learning (FL). By enabling decentralized model training, the framework preserves sensitive employee data while allowing the extraction of meaningful performance insights. Experimental evaluations demonstrate the framework’s effectiveness in achieving high predictive accuracy with minimal privacy risk. The results indicate that federated models can match the performance of centralized approaches while adhering to stringent privacy requirements, offering a scalable and secure solution for modern HR analytics.