Implementasi Metode SVM Untuk Klasifikasi Kelayakan Penerima BPNT
Abstract
Non-cash Food Assistance (BPNT) is a government program that aims to improve the food security of underprivileged communities. However, the process of identifying recipients often faces challenges such as inaccurate data and distribution that is not on target. This research aims to classify the eligibility of BPNT recipients in Bukit Biru Village using the Support Vector Machine (SVM) method. The research data involved 1,041 BPNT recipient data with attributes such as total income, number of dependents, number of vehicles, type of work, marital status and house condition. The research process includes data collection, data transformation preprocessing using One-Hot Encoding, division of Training data and Testing data with a ratio of 80:20. The Support Vector Machine (SVM) model using a linear kernel and optimal parameters such as Complexity (C) = 1000 and maximum iterations = 50 resulted in an accuracy of 89%, with evaluation metrics such as precision, Recall, and F1-Score. These results show that the Support Vector Machine (SVM) method can be used effectively to separate the eligible and ineligible classes. This research is expected to help improve the effectiveness of the BPNT program and provide recommendations for the government in validating prospective recipient data more accurately.Downloads
Download data is not yet available.
Published
2025-04-29
How to Cite
ALI, Sultan.
Implementasi Metode SVM Untuk Klasifikasi Kelayakan Penerima BPNT.
Jurnal Ilmu Komputer, [S.l.], v. 18, n. 1, p. 12, apr. 2025.
ISSN 2622-321X.
Available at: <http://ojs.unud.ac.id/index.php/jik/article/view/124098>. Date accessed: 18 sep. 2025.
doi: https://doi.org/10.24843/JIK.2025.v18.i01.p04.
Section
Articles
Submissions
