Education is the basic capital for the state in developing productive and quality human resources. To produce a good quality education is also influenced by the behavior of children during the school period. Some of the variables that influence children's behavior include the family, environment, play and economic level. From some of these variables, the Random Forest method can be used to predict the success rate of children by processing data based on predetermined variables. To produce a prediction with a high level of accuracy, a method is also needed, namely the Confusion Matrix, to process variables which are input, an online based application is created using Python whose output immediately produces predictions of " Bermasalah" or "Tidak Bermasalah".