Decision Trees for the Early Identification of University Students at Risk of Desertion

Mayra Albán,David Mauricio

doi:10.14419/ijet.v7i4.44.26862

Abstract

The student's dropout at the universities is a topic that has generated controversy in Higher Education Institutions. It has negative effects which cause problems in the social, academic and economic context of the students. One of the alternatives used to predict the dropout at the universities is the implementation of machine learning techniques such as decision trees, known as prediction models that use logical construction diagrams to characterize the behavior of students and identify early students that at in risk of leaving university. Based on a survey of 3162 students, it was possible to obtain 10 variables that have influence into the dropout, that’s why, a CHAID decision tree model is proposed that presents the 97.95% of the accuracy in the prediction of the university students’ dropout. The proposed prediction model allows the administrators of the universities developing strategies for effective intervention in order to establish actions that allow students finishing their university careers successful.

Highlights

The completion of the university has not always been the norm for the society, in the 1940s, less than half of the US population between the ages of 25 and 29 would have finished the university Ye & Bisway [1]
There has existed a concerted effort to close the gap related with the dropout at the universities and decrease its rates, researches that started in 1978 shows that still exists dropout at the universities Abuda & Oda [2] which has caused effects on the economic ambit for Higher Education institutions and governments
The students' dropout from the educational system requires a special interest in the Higher Education Institutions, especially in the public sector

Summary

Introduction

The completion of the university has not always been the norm for the society, in the 1940s, less than half of the US population between the ages of 25 and 29 would have finished the university Ye & Bisway [1]. There has existed a concerted effort to close the gap related with the dropout at the universities and decrease its rates, researches that started in 1978 shows that still exists dropout at the universities Abuda & Oda [2] which has caused effects on the economic ambit for Higher Education institutions and governments. In the literature review were found researches such as those of Marquez [9], Herzog [10], Kotsiantis, et al [11] the authors establish the models of prediction about dropout through experimental processes that consider methods of machine learning supervised to discover knowledge. If the above problems are maintained, the high error rates in the accuracy of the prediction will continue For this reason, it is important to establish a model that allows integrating data, variables and appropriate techniques to accurately predict students at risk of dropping out. The literature review is in the second one, the method is developed in the third, the results of the experimental process is considered in the fourth and in the last part are presented the conclusions

Methods

Results

Discussion

Conclusion