Federated Learning and LSTM-Based Approach for Privacy-Preserving Workforce Management in Global Human Resource Systems

In the data-driven world of today, safeguarding personal information is not only required by law but also essential to upholding operational integrity and confidence. The increasing reliance of firms on data to inform decisions and streamline HR procedures makes this strategy imperative. Traditional methods had problems with scalability and privacy when working with sensitive and varied data sources. The suggested work offers an innovative approach that protects data privacy and permits safe, by combining Federated Learning with LSTM (Long Short-Term Memory). Federated Learning preserves secrecy and complies with privacy requirements. The study's findings show a notable increase in performance, attaining a 99.1% accuracy rate. This increased accuracy demonstrates the method's capacity to uphold strict data privacy rules while offering trustworthy and practical labor management insights. The implementation of the study is done using Python The study opens the door for further developments in safe and effective labor management systems.