Article Per Year (5 Year)
p-Index From 2020 - 2025
0.23
P-Index
This Author published in this journals
All Journal JOMLAI: Journal of Machine Learning and Artificial Intelligence
Permaisuri Siregar
Unknown Affiliation
Computer Science & IT Engineering

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

Found 1 Documents
Search

 1 
Classification of Village Development Index in North Sumatra Using the Support Vector Machine (SVM) Method Yayang Arum Kemangi; Daniel Desmanto Sihombing; Permaisuri Siregar; Sella Ujani; Victor Asido Elyakim P
JOMLAI: Journal of Machine Learning and Artificial Intelligence Vol. 4 No. 3 (2025): September 2025
Publisher : Yayasan Literasi Sains Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55123/jomlai.v4i3.6117

Abstract

The classification of the Village Development Index (IDM) status is a fundamental component in formulating targeted and effective village development policies. However, the conventional classification process is often slow and inefficient, thereby reducing the data's relevance for dynamic decision-making. This research aims to design and evaluate an automatic classification model for the IDM status in 5,417 villages in North Sumatra Province using the Support Vector Machine (SVM) method. By utilizing secondary data from 2024, this model uses three main sub-indices—the Social Resilience Index (IKS), the Economic Resilience Index (IKE), and the Environmental Resilience Index (IKL)—as predictor variables to map villages into five status categories. The implementation of the SVM model with a Radial Basis Function (RBF) kernel was chosen to handle the complex non-linear relationships between variables. The evaluation results on the test data show superior performance, with an overall accuracy rate reaching 96.77%. The model's performance proved to be very strong, particularly in identifying the 'Developing' class with a perfect recall (1.00) and the 'Independent' class with perfect precision (1.00). Although minor challenges were found in distinguishing between adjacent classes such as 'Disadvantaged' and 'Developing', the high F1-score across all classes confirms a good balance between precision and recall. This study concludes that the SVM method is a highly reliable and valid approach for automating IDM classification, and it offers significant implications as a fast and accurate evidence-based decision support tool for local government
Co-Authors Daniel Desmanto Sihombing Sella Ujani Victor Asido Elyakim P Yayang Arum Kemangi