Klasifikasi Status Stunting Menggunakan Algoritma Naive Bayes

Winarni, Eka (2025) Klasifikasi Status Stunting Menggunakan Algoritma Naive Bayes. Skripsi thesis, UIN Imam Bonjol Padang.

	Text (Cover - Daftar Isi) COVER - DAFTAR ISI.pdf - Published Version Download (704kB)
	Text (Bab I) BAB I.pdf - Published Version Download (389kB)
	Text (Bab III) BAB III.pdf - Published Version Download (180kB)
	Text (Bab V - Daftar Pustaka) BAB V - DAFTAR PUSTAKA.pdf - Published Version Download (282kB)
	Text (Full Text) FULL TEXT.pdf - Published Version Restricted to Repository staff only Download (5MB)

Abstract

Stunting is a health problem that is still a concern in Indonesia, especially in Pesisir Selatan Regency which has a fairly high prevalence of Stunting. Stunting can hinder a child's growth and impact the level of intelligence and risk of chronic disease in the future. Therefore, a system is needed that can help classify Stunting status more accurately and efficiently. This research aims to build a Stunting status classification system using the Naive Bayes algorithm, a probability-based classification method that is simple but has a fairly high level of accuracy. This research uses main attributes such as age, gender, birth TB, birth weight, height (TB), and body weight (BB). The system development method used in this research is the Waterfall method, with stages of needs analysis, system design, implementation, Testing and evaluation. The data used in this research was obtained from the Pesisir Selatan District Health Service, which was then processed and tested using the Naïve Bayes algorithm. The research results show that the system built is able to classify Stunting status with the highest level of accuracy at 88.93%. The Naive Bayes algorithm has proven to be effective in processing Stunting data and can be used as a tool to support decision making in the health sector, especially in efforts to prevent and overcome Stunting in areas with high prevalence rates. Keywords: Stunting, Classification, Naive Bayes Algorithm.

Actions (login required)

View Item