DATA MINING CLUSTERING FOOD EXPENDITURE IN INDONESIA

The availability of food in a country is determined by conducive climate. Prolonged droughts, floods, and natural disasters, especially for crop production areas, will have an impact on the disaster conditions faced all countries including Indonesia Covid-19 pandemic, where this affect security Indonesia. Data mining process discovering hidden meaning very large data set. technique used study Mining Clustering validity index Davies-Bouldin. This aims to determine Food Security Strategy through based expenditure Indonesian people's per capita. methodology Cross Industry Standard using K-Means K-Medoids Algorithm. best cluster Algorithm K=7 with value 0.341 Algorithm, it 0.362. research produces algorithm, namely 0.341, which has smaller than results showed that regional. highest average was 5 covering DKI Jakarta area, while lowest 6 Central Java, East Nusa Tenggara, Southeast Sulawesi, Gorontalo, West Sulawesi. In 6, necessary implement strategy increase increasing capacity reserves each region.