<![CDATA[This study aims to analyze and classify the success of Micro, Small, and Medium Enterprises (MSMEs) using a data mining approach based on the entropy-driven Decision Tree (C4.5) algorithm, with the Random Forest algorithm employed as a comparative model. The primary objective of this research is to identify the factors influencing MSME success accurately while providing an interpretable classification model to support business decision-making. The dataset consists of MSME data that underwent a preprocessing stage using one-hot encoding to transform categorical variables into numerical representations. The research methodology includes data exploration, data preprocessing, train-test data partitioning, model development using the C4.5 algorithm, and model evaluation based on accuracy, confusion matrix, classification report, Receiver Operating Characteristic–Area Under the Curve (ROC-AUC), and k-fold cross-validation. In addition, feature importance analysis was conducted to identify the most influential factors affecting MSME success. The findings indicate that the C4.5 algorithm achieved competitive classification performance with stable predictive accuracy while offering a more interpretable model than the Random Forest algorithm. It can therefore be concluded that the C4.5 algorithm is an effective approach for classifying MSME success, as it provides an appropriate balance between predictive accuracy and model interpretability, thereby supporting data-driven decision-making in the MSME sector.]]>
