EARLY WARNING SYSTEM FOR PREDICTING STUDENT GRADUATION USING MACHINE LEARNING METHOD
Education is a key foundation in shaping the future of society. However, challenges such as high dropout rates require a proactive approach to improve the quality and continuity of learning. Early Warning System is one of the instruments that can answer this challenge. By using DRM method, this rese...
Saved in:
| Main Author: | |
|---|---|
| Format: | Theses |
| Language: | Indonesia |
| Online Access: | https://digilib.itb.ac.id/gdl/view/79455 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Institut Teknologi Bandung |
| Language: | Indonesia |
| Summary: | Education is a key foundation in shaping the future of society. However, challenges such as high dropout rates require a proactive approach to improve the quality and continuity of learning. Early Warning System is one of the instruments that can answer this challenge. By using DRM method, this research aims to design an Early Warning System model that can determine graduation classification based on student performance prediction using Machine Learning approach. This prediction model is developed by comparing K-Nearest Neighbors (KNN), Random Forest (RF), and Support Vector Machine (SVM) algorithms. The evaluation results showed that the highest accuracy was achieved by the KNN model with an average value of 93.1% followed by the RF model with an average accuracy of 92.8% and the SVM model with an average value of 90.4%. It is expected that the findings of this research will help in reducing dropout rates in higher education. |
|---|