Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal (JISCO) Journal of Information System and Computing
Sartika Magdalena Sihite
Universitas Negeri Medan
Computer Science & IT

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

Found 1 Documents
Search

 1 
Classification Analysis of Educational Access in Villages Based on School Facilities Using the Support Vector Machine Method with RStudio Aurelya Oktaven Radotia Simangunsong; Grecia Trinatal Simbolon; Riris Sihol Marito Sihombing; Sartika Magdalena Sihite
JISCO : Journal of Information System and Computing Vol 4 No 1 (2026): Journal of Information System and Computing
Publisher : UIN Sulthan Thaha Saifuddin Jambi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30631/jisco.v4i1.5933

Abstract

Educational equity remains one of the major challenges in human resource development in Indonesia. Differences in the availability of educational facilities across regions may affect the quality of educational services and widendevelopment disparities. This study aims to classify educational access levels across regencies/cities in Central Kalimantan Province based on educational facility availability using the Support Vector Machine (SVM) algorithm. Aquantitative approach was employed using secondary data obtained from Statistics Indonesia (BPS) in 2025, consisting of the number of elementary schools, junior high schools, senior high schools, vocational schools, and higher education institutions across 13 regencies/cities. The research procedures included data preprocessing, Min-Max normalization, category labeling usingtertile classification, training-testing data splitting, and SVM model  development. Model performance was evaluated using a confusion matrix and accuracy measurement. The findings indicate that most regencies/cities fallwithin the moderate educational access category, while only a few belong to the high and low categories. The SVM model successfully identified patterns in the distribution of educational facilities with a very high level of accuracy. These results demonstrate the potential of machine learning approaches as decisionsupport tools for educational development planning. Practically, the findings can assist policymakers in prioritizing educational infrastructure development in underserved regions 
Co-Authors Aurelya Oktaven Radotia Simangunsong Grecia Trinatal Simbolon Riris Sihol Marito Sihombing