<![CDATA[Student graduation is an indicator of the success of the educational process which is influenced by several factors, such as grades, extracurricular activities, interpersonal, non-academic, parental support, cognitive abilities. Predictions of student graduation can provide valuable information for schools to identify students at risk of not graduating and provide appropriate intervention. This research aims to develop a prediction model for student graduation using the Support Vector Machine (SVM) method. The data used includes academic grades, extracurricular activities, socio-economic conditions, and other relevant factors. The SVM method was chosen because of its ability to find the optimal hyperplane that maximally separates data classes. The modeling process includes data cleaning, feature selection, SVM parameter optimization, and performance evaluation using metrics such as accuracy, precision and recall. The research results show that the SVM model developed is able to predict student graduation with an accuracy of 95.06%. Model analysis reveals the main factors that influence student graduation, in an effort to increase student graduation rates. ]]>
Copyrights © 2024
