Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal Jurnal Krisnadana
Ni Luh De Sri Chandra Purahita
Program Studi Informatika, Fakultas Teknologi dan Informatika, Institut Bisnis Dan Teknologi Indonesia, Denpasar, Bali, Indonesia
Computer Science & IT Control & Systems Engineering

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
AI-Based Model for Predicting On-Time Graduation of INSTIKI Students Using K-NN and Particle Swarm Optimization Made Leo Radhitya; I Made Dwi Asana; Ni Luh De Sri Chandra Purahita; I Made Subrata Sandhiyasa; I Nyoman Tri Anindia Putra
Jurnal Krisnadana Vol 5 No 1 (2025): Jurnal Krisnadana- in Progress September-October 2025
Publisher : Yayasan Sinergi Widya Nusantara (Sidyanusa)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58982/krisnadana.v5i1.930

Abstract

This study aims to enhance the accuracy and generalization capability of student on-time graduation prediction by integrating the K-Nearest Neighbor (K-NN) algorithm with Particle Swarm Optimization (PSO) for parameter tuning. Historical academic records from INSTIKI were used as the primary dataset, and a 10-fold cross-validation technique was applied to ensure robust evaluation. The PSO algorithm was employed to determine the optimal k value for K-NN, with optimization parameters set to c1 = 0.5, c2 = 0.6, inertia weight w = 0.9, swarm size = 90 particles, and 100 maximum iterations. The optimized model achieved an optimal k = 23, resulting in a validation accuracy of 77.84%, outperforming the baseline K-NN’s 72.43%. In addition, improvements were observed in precision, recall, F1-score, and AUC, with the latter increasing from 0.56 to 0.68, indicating better discrimination capability. These results demonstrate that PSO effectively mitigates overfitting and enhances model stability compared to conventional K-NN. The proposed approach offers a reliable and scalable predictive model for academic early-warning systems, enabling institutions to identify at-risk students earlier and implement targeted interventions. Future work may involve incorporating non-academic features, addressing class imbalance, and exploring ensemble learning for further performance gains.
Co-Authors I Made Dwi Asana I Made Subrata Sandhiyasa I Nyoman Tri Anindia Putra Made Leo Radhitya