Educational Data Mining to Predict Students Performance Based on Deep Learning Neural Network

Abstract

Recently, educational data mining has become very helpful in decision making in an educational context and hence improving students’ academic outcomes. Thus, the goal of this study was to create a predictive model to predict students’  academic performance based on a neural network algorithm. Authors implemented a Neural Network data mining technique using Anaconda 3 as datamining tool to extract knowledge patterns from student’s dataset consisting of 131 students with 22 attributes for each student. The classification metric used is accuracy as the model quality measurement. The result indicates that when SGD optimizer was applied, the accuracy was below 80%. While, when Adam optimization technique was applied the accuracy improved to more than 96% which is more than a satisfactory percentage for our predictive model. This indicates that the suggested NN model can be reliable for prediction, especially in social science studies like education.