Predicting Dropout Student: An Application of Data Mining Methods in an Online Education Program

Abstract

This study examined the prediction of dropouts through data mining approaches in an online program. The subject of the study was selected from a total of 189 students who registered to the online Information Technologies Certificate Program in 2007-2009. The data was collected through online questionnaires (Demographic Survey, Online Technologies Self-Efficacy Scale, Readiness for Online Learning Questionnaire, Locus of Control Scale, and Prior Knowledge Questionnaire). The collected data included 10 variables, which were gender, age, educational level, previous online experience, occupation, self efficacy, readiness, prior knowledge, locus of control, and the dropout status as the class label (dropout/not). In order to classify dropout students, four data mining approaches were applied based on k-Nearest Neighbour (k-NN), Decision Tree (DT), Naive Bayes (NB) and Neural Network (NN). These methods were trained and tested using 10-fold cross validation. The detection sensitivities of 3-NN, DT, NN and NB classifiers were 87%, 79.7%, 76.8% and 73.9% respectively. Also, using Genetic Algorithm (GA) based feature selection method, online technologies self-efficacy, online learning readiness, and previous online experience were found as the most important factors in predicting the dropouts.

Goal Orientation and Academic Performance in Adult Distance Education

“…A common problem in all higher education, but especially in distance education, is the high dropout and low retention rate (Berge & Huang, 2004;Yukselturk, Ozekes, & Türel, 2014). Knowing what motivates students to follow courses in distance education in the first place, and knowing the relationship between their goal to study and academic performance might be valuable information to heighten the retention rate for adult distance learners.…”

Um Modelo Preditivo da Evasão dos Alunos na EAD a Partir dos Construtos da Teoria da Distância Transacional

“…Obra Algoritmos/Técnicas Acurácia [Kotsiantis et al, 2003] Naive Bayes 83% [Morris et al, 2005] Análise Discriminante Preditiva 74,5% [Roblyer et al, 2008] Regressão logística 79,3% [Lykourentzou et al, 2009] Combinação de técnicas 85% [Kovacic, 2010] Árvore de Decisão 60,5% [Yasmin, 2013] Árvore de Decisão 84,8% [Yukselturk et al, 2014] Redes Neurais 87% [Rigo et al, 2014] Redes Neurais 76,5% [Cambruzzi, 2014] Redes Neurais 75,7% [Dos Santos et al, 2014] Árvore de Decisão 81,64% [Silva et al, 2015] Árvore de Decisão 73,37% [Queiroga et al, 2015] Vários 79,76%…”

A multi hidden recurrent neural network with a modified grey wolf optimizer

“…In [19], a decision tree, neural network, nearest neighbor, and naïve Bayes classifier were used to forecast dropouts in an online program. A 10-fold crossvalidation was used.…”