<![CDATA[Employee attrition is a critical issue in human resource management as it directly affects a company’s productivity and operational efficiency. Therefore, a data-driven prediction system is needed to identify potential employee resignation risks at an early stage. This study aims to build an employee attrition classification model using the Random Forest algorithm, implemented in the RapidMiner software. The dataset used in this study is derived from the IBM HR Analytics Employee Attrition Dataset. The research process includes data cleaning, attribute transformation, model building, and performance evaluation using a confusion matrix and metrics such as accuracy, precision, and recall. The results show that the Random Forest model achieved an accuracy of 91.04%, a precision of 100% for the “Yes” class, and a recall of 44.37%. Furthermore, it was found that the variables JobLevel and TotalWorkingYears significantly influence attrition status. Therefore, this model can serve as a decision support tool in identifying employee attrition risks and designing more effective, data-driven retention strategies]]>
Copyrights © 2025
