<![CDATA[Job promotion is an important factor in human resource management as it can enhance employee motivation, loyalty, and performance. This study aims to build a job promotion prediction model using the Gradient Boosting Machines (GBM) algorithm implemented in RapidMiner Studio. The dataset used was sourced from Kaggle, consisting of 54,808 training records and 23,491 testing records. The research process included data preprocessing, splitting into training and testing sets, model training, performance evaluation using metrics such as accuracy, precision, recall, F1-score, and AUC, and applying the model to actual test data. The developed GBM model achieved an accuracy of 91.10% and an AUC value of 0.776. The prediction results on the test data indicated that approximately 84.4% of employees were predicted as not eligible for promotion, while 15.6% were predicted as eligible. These findings demonstrate that a machine learning approach can help companies make job promotion decisions more objectively, transparently, and data-driven.]]>
Copyrights © 2025
