<![CDATA[Student academic performance is one of the important indicators of success in the learning process. Therefore, a method is needed that can analyze and accurately predict students' academic performance. This study aims to analyze and predict students' academic performance using the Random Forest algorithm. The dataset used consists of 649 student records with 33 attributes covering student characteristics, family background, social activities, and academic grades. The students’ final grade (G3) is used as the target variable in the classification process.The research stages include data exploration, data preprocessing, splitting the data into training and testing sets, building the Random Forest model, and evaluating the model. The results show that the Random Forest model is able to achieve an accuracy rate of 92.31%. Testing using a confusion matrix indicates that the model has a relatively low prediction error rate. In addition, testing using the cross-validation method produces an average accuracy of 91.21%, indicating that the model has good stability. Feature importance analysis shows that previous academic grades, namely G2 and G1, are the most influential factors affecting students' academic performance. The results of this study indicate that the Random Forest algorithm can be effectively used to predict students' academic performance and can assist educational institutions in data-driven decision-making.]]>
Copyrights © 2026
