Evaluation of Prediction Algorithms in the Student Dropout Problem

Luis Earving Lee,Emilio Castán Rocha,Salvador Ibarra Martínez,Julio Laria Menchaca,Mayra Guadalupe Treviño Berrones,Jesús David Terán Villanueva,José Antonio Castán Rocha

doi:10.4236/jcc.2020.83002

Luis Earving Lee, Emilio Castán Rocha + Show 5 more

Open Access

https://doi.org/10.4236/jcc.2020.83002

Copy DOI

Abstract

University dropout is a growing problem which, in recent years, is using computer techniques to assist in the detection process. The paper presents the evaluation of some prediction algorithms to detect a student with a high possibility of scholar desertion. The approach uses real data from past scholar periods to create a dataset with different information of the students (i.e., personal, economic, and academic records). The algorithms selected in the experimental phase were: J48 decision tree, K-near neighbors, and support vector machine. We use two similarity metrics to split the dataset with cases with at least 80% of similarity to evaluate each case. We use the data from 2010 to 2016 with real students’ information to predict if there exists the possibility of a real academic dropout in one test for a period. The results show that the J48 algorithm reaches a better performance in both experiments. Besides, the tree generated for each student is taken as a path of attention, reaching around 88% of effectiveness. Finally, the conclusions argue the contributions of the paper and propose a future line of research.

Highlights

In the last ten years, the scholar desertion arises as one of the most studied problems by academic organisms
The algorithms selected in the experimental phase were: J48 decision tree, K-near neighbors, and support vector machine
The results indicate that J48 is a suitable and useful method to classify all the dropouts

Summary

Introduction

In the last ten years, the scholar desertion arises as one of the most studied problems by academic organisms. In reference [4], the authors propose the implementation of a decision tree using the Gini index, as a classification model to detect dropout with students in online courses of the second year. All the above works are a feasible example of current approaches with suitable and robust results that looks for providing academic solutions to our students in time and form. They only care about the identification of a potential dropout without committing to offer a reliable solution to the lecturer of the course or the academic tutor.

Implementation of the Approach

Experiments and Results

Conclusion