KLASIFIKASI PENERIMA BANTUAN IURAN JAMINAN KESEHATAN DI NTB MENGGUNAKAN REGRESI LOGISTIK BINER DAN NAÏVE BAYES

Authors : Jihan Melani; Zulhan Widya Baskara; Lisa Harsyiah
article cite 0 Year 2025
source: Jurnal Gaussian
Abstract

Health and poverty are two things that always go hand in hand and are included in Sustainable Development Goals or what are known as SDGs. As the SDGs progress, several countries have attempted to provide social assistance programs aimed at overcoming poverty and providing access to health services for their communities, as is done in Indonesia. BPJS Recipient Contribution Assistance (PBI) health insurance is one of the assistance provided in the form of health insurance contribution assistance to the poor or underprivileged people. This study aims to classify the status of recipients of health insurance contribution assistance in NTB using binary logistic regression and naïve Bayes methods. The independent variables used are house floor area, house floor type, house wall type, defecation facilities, main light source, main water source, type of material burning for cooking, and final education. The results obtained show that Naïve Bayes is better at classifying the status of recipients of health insurance contribution assistance in NTB compared to binary logistic regression, with the classification rates of binary logistic regression and naïve bayes are 62.26% and 63.9%.


Concepts :
Data Mining and Machine Learning Applications
Management and Optimization Techniques
article cite 0 Year 2025 source Jurnal Gaussian
SDGs
Partnerships for the goals
Citations by Year
YearCount
2025 0