Application of Machine Learning for Academic Outcome Prediction: A Methodological Comparative Study

Academic performance prediction is a crucial area in education; however, the complexity of influencing factors often cannot be adequately captured by simple linear models. This research conducts a methodological comparative analysis of five machine learning models Simple Linear Regression, Multiple...

Full description

Saved in:
Bibliographic Details
Main Authors: Md. Wira Putra Dananjaya, Putu Gita Pujayanti
Format: Article
Language:English
Published: Pusat Penelitian dan Pengabdian Masyarakat (P3M), Politeknik Negeri Cilacap 2025-06-01
Series:Journal of Innovation Information Technology and Application
Subjects:
Online Access:https://ejournal.pnc.ac.id/index.php/jinita/article/view/2540
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849425523664486400
author Md. Wira Putra Dananjaya
Putu Gita Pujayanti
author_facet Md. Wira Putra Dananjaya
Putu Gita Pujayanti
author_sort Md. Wira Putra Dananjaya
collection DOAJ
description Academic performance prediction is a crucial area in education; however, the complexity of influencing factors often cannot be adequately captured by simple linear models. This research conducts a methodological comparative analysis of five machine learning models Simple Linear Regression, Multiple Linear Regression (MLR), Decision Tree, Random Forest, and Artificial Neural Network (ANN) to determine the most accurate predictive approach using a comprehensive dataset encompassing academic, behavioral, and psychosocial factors. The models were evaluated using Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and R-squared (R2) metrics. Evaluation results on the test data revealed that the Multiple Linear Regression (MLR) model unexpectedly delivered the most superior performance, achieving an R2 value of 0.7324 and the lowest RMSE of 2.0391. Further analysis from non-linear models identified Attendance and Hours_Studied as the two factors with the highest predictive influence. This study concludes that interpretable models like MLR can be highly effective when supported by relevant features, offering practical implications for institutions to develop effective early warning systems by focusing on key, actionable factors.
format Article
id doaj-art-36b6d876ef2e420aa1470ef41c9cb833
institution Kabale University
issn 2716-0858
2715-9248
language English
publishDate 2025-06-01
publisher Pusat Penelitian dan Pengabdian Masyarakat (P3M), Politeknik Negeri Cilacap
record_format Article
series Journal of Innovation Information Technology and Application
spelling doaj-art-36b6d876ef2e420aa1470ef41c9cb8332025-08-20T03:29:44ZengPusat Penelitian dan Pengabdian Masyarakat (P3M), Politeknik Negeri CilacapJournal of Innovation Information Technology and Application2716-08582715-92482025-06-0171435210.35970/jinita.v7i1.25401652Application of Machine Learning for Academic Outcome Prediction: A Methodological Comparative StudyMd. Wira Putra Dananjaya0Putu Gita Pujayanti1Universitas Pendidikan NasionalUniversitas Pendidikan GaneshaAcademic performance prediction is a crucial area in education; however, the complexity of influencing factors often cannot be adequately captured by simple linear models. This research conducts a methodological comparative analysis of five machine learning models Simple Linear Regression, Multiple Linear Regression (MLR), Decision Tree, Random Forest, and Artificial Neural Network (ANN) to determine the most accurate predictive approach using a comprehensive dataset encompassing academic, behavioral, and psychosocial factors. The models were evaluated using Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and R-squared (R2) metrics. Evaluation results on the test data revealed that the Multiple Linear Regression (MLR) model unexpectedly delivered the most superior performance, achieving an R2 value of 0.7324 and the lowest RMSE of 2.0391. Further analysis from non-linear models identified Attendance and Hours_Studied as the two factors with the highest predictive influence. This study concludes that interpretable models like MLR can be highly effective when supported by relevant features, offering practical implications for institutions to develop effective early warning systems by focusing on key, actionable factors.https://ejournal.pnc.ac.id/index.php/jinita/article/view/2540machine learningacademic performance predictioncomparative analysis
spellingShingle Md. Wira Putra Dananjaya
Putu Gita Pujayanti
Application of Machine Learning for Academic Outcome Prediction: A Methodological Comparative Study
Journal of Innovation Information Technology and Application
machine learning
academic performance prediction
comparative analysis
title Application of Machine Learning for Academic Outcome Prediction: A Methodological Comparative Study
title_full Application of Machine Learning for Academic Outcome Prediction: A Methodological Comparative Study
title_fullStr Application of Machine Learning for Academic Outcome Prediction: A Methodological Comparative Study
title_full_unstemmed Application of Machine Learning for Academic Outcome Prediction: A Methodological Comparative Study
title_short Application of Machine Learning for Academic Outcome Prediction: A Methodological Comparative Study
title_sort application of machine learning for academic outcome prediction a methodological comparative study
topic machine learning
academic performance prediction
comparative analysis
url https://ejournal.pnc.ac.id/index.php/jinita/article/view/2540
work_keys_str_mv AT mdwiraputradananjaya applicationofmachinelearningforacademicoutcomepredictionamethodologicalcomparativestudy
AT putugitapujayanti applicationofmachinelearningforacademicoutcomepredictionamethodologicalcomparativestudy