Dropout Prediction System to Enhance Massive Open Online Courses

Abstract

Statistics have shown a growth rate of 120% from 2019 to the end of 2020 in MOOCs Courses around the world. This research proposes a new methodology in predicting student result in MOOCs modules. Since dropouts and failure rates of MOOCs’ students is a well noticed problem, the proposed methodology contributed a new model that uses various feature selection algorithms and Probabilistic Neural Network (PNN) classification algorithm. Results showed that using certain feature selection algorithms in combination with PNN resulted in enhancing trend exploration and prediction.