Development of a Web-Based Prediction System for Students’ Academic Performance

Dabiah Alboaneen,Renad Alharthi,Rawan Alsubaie,Modhe Almelihi,Lama Alshehri,Raneem Alghamdi

doi:10.3390/data7020021

Dabiah Alboaneen, Renad Alharthi + Show 4 more

Open Access

https://doi.org/10.3390/data7020021

Copy DOI

Journal: Data	Publication Date: Jan 29, 2022
Citations: 15	License type: CC BY 4.0

Affiliation: Imam Abdulrahman Bin Faisal University

Abstract

Educational Data Mining (EDM) is used to extract and discover interesting patterns from educational institution datasets using Machine Learning (ML) algorithms. There is much academic information related to students available. Therefore, it is helpful to apply data mining to extract factors affecting students’ academic performance. In this paper, a web-based system for predicting academic performance and identifying students at risk of failure through academic and demographic factors is developed. The ML model is developed to predict the total score of a course at the early stages. Several ML algorithms are applied, namely: Support Vector Machine (SVM), Random Forest (RF), K-Nearest Neighbors (KNN), Artificial Neural Network (ANN), and Linear Regression (LR). This model applies to the data of female students of the Computer Science Department at Imam Abdulrahman bin Faisal University (IAU). The dataset contains 842 instances for 168 students. Moreover, the results showed that the prediction’s Mean Absolute Percentage Error (MAPE) reached 6.34%, and the academic factors had a higher impact on students’ academic performance than the demographic factors, the midterm exam score in the top. The developed web-based prediction system is available on an online server and can be used by tutors.

Highlights

The academic performance of students is an essential part of education
The Mean Absolute Percentage Error (MAPE) of Support Vector Machine (SVM) and Linear Regression (LR) are close to Random Forest (RF)
On the other hand, when using DS2, LR achieved the lowest MAPE with 6.34%, and the SVM had a good MAPE with 6.40% that very close to the LR followed by RF with a MAPE of 7.05%

Summary

Introduction

The academic performance of students is an essential part of education. Students with low academic performance will face many issues, such as late graduation and even dropping out [1,2]. Educational institutions should monitor their students’ academic performance closely and support low performing students immediately. One method to achieve that is by predicting students’ academic performance [1]. Using this method will help educational institutions to identify and support low performing students at an early stage. Prediction of students’ academic performance can assist educational institutions to take the appropriate action at the right time, and making a suitable plan to improve the academic performance of low performing students [3]. Predicting students’ academic performance accurately can be challenging as it is influenced by numerous factors (e.g., academic, marital, and economic factors) [4,5]

Objectives

Results

Conclusion