Competitive business environment demands that employees are a vital component of organizational success. The investment in professional training, the strong bonds of loyalty developed over time, and the significance of certain key positions make it imperative for organizations to proactively identify employees at risk of leaving. Various factors can contribute to employee attrition, and understanding these factors is essential for minimizing turnover and retaining talent. This study aims to leverage machine learning techniques to predict employee attrition accurately. By utilizing the IBM attrition dataset, we explore the effectiveness of different machine learning models, including SMOTE and weighted Logistic Regression in forecasting employee turnover. The goal is to develop robust predictive models that can help organizations identify at-risk employees, enabling them to tailor retention strategies effectively and foster higher levels of employee engagement and satisfaction