Integrating Machine Learning in Outcome-Based Learning Systems: A Predictive Approach

Tjandra, Ellysa and Setiawan, Noor Akhmad (2026) Integrating Machine Learning in Outcome-Based Learning Systems: A Predictive Approach. In: 2025 17th International Conference on Information Technology and Electrical Engineering (ICITEE), 20-21 October 2025, Bangkok, Thailand.

PDF Gabungan Naskah ICITEE2025.pdf - Published Version Download (5MB)

Abstract

Outcome-Based Education (OBE) emphasizes achieving measurable learning outcomes as an indicator of academic success. However, conventional evaluation approaches often fail to provide accurate and timely predictions of student performance consistent with these outcomes. This study proposes a new system that utilizes machine learning (ML) methods in an OBE-based education setup to rapidly identify students who may be struggling and provide them with data-driven support. Multiple supervised learning algorithms were trained and evaluated using a dataset that includes student performance indicators based on mid-term assessment scores, including Decision Tree, Random Forest, K-Nearest Neighbor, Support Vector Classification, Naïve Bayes, XGBoost, and AdaBoost. The dataset comprises 2,130 records of students’ scores in 14 courses from 7 study programs of a private university in Indonesia. This research finds that XGBoost classification yields the best results in predicting course outcomes for low-participant courses, with a maximum accuracy of 91.36%. In comparison, Naïve Bayes achieves the highest accuracy for high-participant classes (86.89%). This study also examined the relationship between the number of student outcomes, the number of mid-term assessment components, and model accuracy results, and found that the greater the number of student outcomes and mid-term assessments, the lower the model accuracy results.

Item Type:	Conference or Workshop Item (Paper)
Uncontrolled Keywords:	machine learning, prediction, OBE, learning system
Subjects:	L Education > L Education (General) Q Science > Q Science (General)
Divisions:	Faculty of Engineering > Department of Informatic
Depositing User:	Ellysa Tjandra 61144
Date Deposited:	21 Jan 2026 05:30
Last Modified:	21 Jan 2026 05:30
URI:	http://repository.ubaya.ac.id/id/eprint/50164

Actions (login required)

View Item