Predicting Students’ Academic Performance Using Correlation and Regression Analysis

Document Type

Conference Proceeding

Source of Publication

Lecture Notes in Networks and Systems

Publication Date

9-1-2025

Abstract

Modern digital learning systems are becoming more student-centered than means of traditional learning due to the opportunities for monitoring and predicting student academic performance. As an experiment, the dependence of student academic performance on the number of test scores during the semester was analyzed. By means of correlation and regression analysis the general tendencies specific to the educational process were revealed. The main advantage of the obtained results is the opportunity to use them in predicting student learning outcomes. The closer the value of the coefficient of determination to one the higher the prediction accuracy. Thus, having calculated the linear regression and Pearson correlation coefficients for several tests and the final grade for the course, it is possible to choose the regression that can provide the most reliable prediction of students’ academic performance. #COMESYSO1120.

ISSN

2367-3370

Publisher

Springer Nature Switzerland

Volume

1491

First Page

285

Last Page

297

Disciplines

Education

Keywords

Correlation, Digital Learning, LMS Moodle, Pearson Correlation Coefficient, Regression, Student’s T-test

Scopus ID

105018573542

Indexed in Scopus

yes

Open Access

no

Link to Full Text

Share

COinS