Efficient Performance Prediction in Cloud-Based HR Systems Using Federated Learning

Abstract

Cloud-based Human Resource (HR) systems have transformed how organizations manage employee data and performance evaluation. While centralized systems offer convenience, they also pose challenges related to data privacy and security. Federated Learning (FL) has emerged as a promising paradigm that allows collaborative learning across distributed datasets without exposing sensitive employee information. This paper investigates the application of FL for efficient performance prediction in cloud-based HR platforms, focusing on privacy preservation, computational efficiency, and predictive accuracy. Experimental results demonstrate that the FL-based approach significantly improves model generalization and resilience to attacks, providing organizations with reliable and secure performance insights. The study also evaluates performance under different data distributions and simulated attack scenarios, emphasizing the role of FL in safeguarding both analytics quality and data privacy.