A Self-Adjusting Approach for Temporal Dropout Prediction of E-Learning Students

This work proposes a dropout prediction approach that is able to self-adjust their outcomes at any moment of a degree program timeline. To that end, a rule-based classification technique was used to identify courses, grade thresholds and other attributes that have a high influence on the dropout behavior. This approach, which is generic so that it can be applied to any distance learning degree program, returns different rules that indicate how the predictions are adjusted along with academic terms. Experiments were carried out using four rule-based classification algorithms: JRip, OneR, PART and Ridor. The outcomes show that this approach presents better accuracy according to the progress of students, mainly when the JRip and PART algorithms are used. Furthermore, the use of this method enabled the generation of rules that stress the factors that mainly affect the dropout phenomenon at different degree moments.