Employees are the foundation of any organization, and their well-being plays an important role in maintaining a productive and stable workforce. However, layoffs, often caused by economic challenges or company changes, can greatly affect both employees and businesses. This paper illustrates a predictive system that utilizes the XGBoost algorithm to forecast employee layoffs in organizations. With layoffs being an inevitable part of organizational restructuring or economic challenges, the proposed system helps mitigate their impact by not only predicting layoffs but also providing personalized skill recommendations to at-risk employees. The system is built using the IBM HR Analytics dataset and demonstrates an accuracy of 87.76% in predicting layoffs, making it a valuable tool for HR management and workforce development. Several machine learning models such as Random Forest, SVM, Decision Trees, Naive Bayes, and XGBoost were tested and compared to find the most effective one for the task. Among these models, XGBoost performed the best in terms of key metrics like accuracy, precision, and recall. This implies that XGBoost was more reliable in making correct predictions and reducing errors compared to other models. Its ability to handle complex data and optimize performance made it stand out.