Student Dropout Predictive Model Using Data Mining Techniques

Abstract

Data mining allows discover hidden information in large amounts of data, which is very difficult to visualize with traditional process. This topic of computer science permits manipulation and classification of huge amounts of data. C4.5 and ID3 decision tree, for example, have been proven to be efficient for specific prediction cases. This article shows the construction of a predictive model of student dropout, characterizing students at the University Simon Bolivar in order to predict the probability that a student drop out his/her an academic program, by means of two data mining techniques and comparison of results. To create the model was used WEKA that allows multiple and efficient tools for data processing