Improving Academic Performance Prediction by Dealing with Class Imbalance

Abstract

Abstract-This paper introduces and compares some techniques used to predict the student performance at the university. Recently, researchers have focused on applying machine learning in higher education to support both the students and the instructors getting better in their performances. Some previous papers have introduced this problem but the prediction results were unsatisfactory because of the class imbalance problem, which causes the degradation of the classifiers. The purpose of this paper is to tackle the class imbalance for improving the prediction/classification results by over-sampling techniques as well as using cost-sensitive learning (CSL). The paper shows that the results have been improved when comparing with only using baseline classifiers such as Decision Tree (DT), Bayesian Networks (BN), and Support Vector Machines (SVM) to the original data sets.

Giải Pháp Hỗ Trợ Sinh Viên Lập Kế Hoạch Học Tập Dựa Trên Tiếp Cận Tập Thô

“…Thuộc tính cần dự đoán có phân phối 15 5/1 9 5 tương ứng với hai lớp "cảnh báo"/ "không cảnh báo". Tập dữ liệu này thuộc dạng mất cân bằng (imbalanced data) do chỉ có 8.01% thuộc lớp số ít (minority class) [7][9].…”

Matrix and Tensor Factorization for Predicting Student Performance

“…decision trees and Bayesian networks) for predicting academic performance; while (Thai-Nghe et al, 2009) proposed to improve the student performance prediction by dealing with the class imbalance problem. (i.e., the ratio between passing and failing students is usually skewed).…”

“…Most of them relying on traditional methods such as logistic regression (Cen et al, 2006), linear regression (Feng et al, 2009), decision tree (Thai-Nghe et al, 2007), neural networks (Romero et al, 2008), support vector machines (Thai-Nghe et al, 2009), and so on.…”

Factorization Techniques for Predicting Student Performance

“…Most of them rely on traditional methods such as neural networks (Romero et al, 2008), Bayesian networks (Bekele and Menzel, 2005), logistic regression (Cen et al, 2006), support vector machines (Thai-Nghe et al, 2009) and so on.…”

“…to classify students based on their Moodle usage data and the final marks obtained in their respective courses; Bekele and Menzel (2005) used Bayesian networks to predict student results; Cen et al (2006) proposed a method for improving a cognitive model, which is a set of rules/skills encoded in intelligent tutors to model how students solve problems, using logistic regression; Thai-Nghe et al (2007) analyzed and compared some classification methods (e.g. decision trees and Bayesian networks) for predicting academic performance; while Thai-Nghe et al (2009) proposed to improve the student performance prediction by dealing with the class imbalance problem using support vector machines (i.e., the ratio between passing and failing students is usually skewed).…”