Evidence record · UDINUS · SDGs
- Unit
- Rektorat UDINUS
- Period
- 2020
- Goals
- Record
- 97e6b165-e1c5-438c-af48-82ac5f870388
- Published
- 2026-10-30
Universitas Dian Nuswantoro conducted an activity on learning progress modeling for monitoring students. Researchers Arafiyah, Ria; Hasibuan, Zainal A.; and Budi Santoso, Harry participated in the activity. The activity addressed the monitoring of student progress, which is described as an important and very time-consuming part of a teacher's work, particularly when teachers manage many students and various subjects. The source presents this situation as the experience of most primary school teachers in Indonesia.
The activity examined prediction of student progress as one way to support this monitoring process. The Random Forest algorithm was used because it can classify data with incomplete attributes, which are usually found in student assessment data. The prediction model was built from assessment data involving two classes and 46 elementary school students. The subjects covered Indonesian, mathematics, SBdP (Cultural Arts and Crafts), PPKN (Pancasila and Citizenship Education), and Computers. The dataset consisted of formative and summative assessment results from three aspects: cognitive, psychomotor, and affective.
Model performance was measured using accuracy and recall. For the dataset covering five subjects and 46 students, the Random Forest algorithm produced a learning progress model with 100% accuracy for the training data and 94% accuracy for the testing data. The learning progress prediction model for each subject achieved 100% accuracy on the training data and more than 96% accuracy on the test data. These findings describe the performance of the model within the assessment data used in the activity.
In relation to the stated goal concerning learning progress modeling for monitoring students, the activity concerns research on learning progress and the use of assessment information in primary education. It provides evidence about a model for predicting student progress across specified subjects and assessment aspects. Through this activity, UDINUS documented research focused on understanding and modeling student learning progress.