Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
October 13, 2025JURNAL TEKNIK INFORMATIKA

Addressing Class Imbalance in Machine Learning for Predicting On-Time Student Graduation at The Islamic University of Riau

View Full Paper
Ask AI
Bookmark
Share

Authors

AEAkmar EfendiIslamic University of RiauSDSarjon DefitUniversitas Putra Indonesia "YPTK"

Discussion

Loading...

Member takes

Implication

Analysis reveals class imbalance affects machine learning accuracy in predicting graduation, highlighting SMOTE's role.

Key Points

  • Applying SMOTE significantly improved machine learning model performance, achieving nearly 99% accuracy.
  • Results indicated that Support Vector Machine demonstrated the most consistent outcomes across different conditions.
  • Timely graduation data from Islamic University of Riau was analyzed to understand the effects of class imbalance on predictions.
  • This study may enable universities to implement early intervention strategies for students at risk of graduation delays.

Cite This Study

Efendi et al. (2025) studied this question.

synapsesocial.com/papers/68ed4e04d3b1bfa344c601b1https://doi.org/10.15408/jti.v18i2.45913
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Ensemble-SMOTE: Mitigating Class Imbalance in Graduate on Time Detection2024 · 10 citations
  2. 2Algorithmic Prediction of Students On-Time Graduation from the University2024 · 11 citations
  3. 3Comparative Analysis of Gradient Boosting, XGBoost, and KNN on Predicting Student Graduation in Imbalance and Balance Data Schemes2025 · 1 citations
  4. 4Evaluating Random Forest Algorithm in Educational Data Mining: Optimizing Graduation on-time prediction using Imbalance Methods2024 · 6 citations
  5. 5Comparison of Classification Algorithms for Predicting Graduation of Informatics Engineering Students with Orange Data Mining2024