Malaysia has been struggling to sustain the number of students graduating from school, with an increasing number leaving early, which poses significant concerns for the future generation. Several factors contribute to this issue, such as economic constraints, geographical challenges, transportation problems, and sociocultural norms. This paper uses a data mining approach to identify the attributes that lead to school dropouts and to determine the predictive model with the highest accuracy for forecasting dropout rates. The application of data mining approaches has proven effective in predicting students at risk of dropping out in general education. Nevertheless, there is a shortage of data mining-related studies on student attrition in public schools in Malaysia. The study utilized student and school datasets with consent from the respective departments in the Ministry of Education. This data includes information from 2,482 students across various primary schools in Selangor with initially 22 attributes collected from the dataset. After the attributes undergone feature selection process by using InfoGainAttributeEval, there are 12 features left including class attribute Status_DO. The collected data encompasses student demographics, academic performance and socioeconomic background. The experiments for this study used Decision Trees (J48), Naïve Bayes and Random Forest. By using classification techniques that were made available in WEKA, all attributes from the dataset were tested. The results of the analysis shown that Random Forest with the highest accuracy of 79.5729% in term of predicting student drop out hence indicate the reliability of this research as a decision support tool.