A Comparative Study of School Parent Satisfaction Predictors using different Classifiers

Educational data mining (EDM) is applied on voluminous student information for obtaining some useful information. This research focuses on the parents' satisfaction based on their executed study. Instead of focusing only from the educational institutions, it is also required to put concentration to the parents’ side. Depending on the factors such as how the student carries out their study, their examination result and many more, parental satisfaction is predicted. For carrying out the analysis of these parameters, machine learning methods are implemented and applied to the educational dataset. Several machine learning models such as Support Vector Machines (SVM), k-Nearest Neighbours (KNN), Decision Tree classifiers, and Multi-layer Perceptron classifier (MLP) are constructed for predicting parental satisfaction level. Comparative analysis shows the highest accuracy of 92% executed by the SVM model. Executing this predictive modeling will assist the parents to guide and motivate their children towards areas that demand improvement.