Penerapan Data Mining Algoritma Apriori untuk Menemukan Pola Hubungan Status Gizi Balita

Abstract

Malnutrition of toddlers can cause severely health problems, growth retardation, and decreased intelligence. Therefore, it is important to know the pattern of the relationship between the nutritional status of toddlers, especially against the condition of malnutrition to get information about the possible risk of nutritional coexistence problems. The purpose of this research is to apply data mining using the apriori algorithm in finding patterns of relationships between
nutritional status and to produce an accuracy level of association rules based on the value of support, confidence, and validation with the lift ratio. The results of this study are expected to generate information that can help prevent and treat malnutrition, as well as appropriate nutrition interventions. Analysis and implementation of data using the a priori algorithm method. Manual calculations are carried out using Microsoft Excell and accurate calculations with python programming. Data on the nutritional status of children under five, especially undernourished conditions will be processed to find patterns of association relationships. Determined the minimum support value of 0.1 or 10% and the minimum confidence of 0.5 or 50%. The research produces association rules in the form of association relationship patterns of nutritional status specifically malnutrition conditions (Underweight?Stunting ) with a support of 0.25 or 25% and confidence 0.57 or 57%. The rules have met the minimum support and minimum confidence values and have been validated by the lift ratio with a value > 1.