Utilization of Data Mining Techniques in National Food Security during the Covid-19 Pandemic in Indonesia
Zulhipni Reno Saputra Elsi, Heny Pratiwi, Yoyon Efendi, R Rusdina, Rina Alfah, Agus Perdana Windarto, Fana Wiza
Abstract
Abstract The aim of the research is to map clusters on Indonesia’s national food security during the Covid-19 Pandemic. Where food security is a condition for the fulfillment of food for the state up to individuals, which is reflected in the availability of sufficient food, both in quantity and quality, safe, diverse, nutritious, equitable, and affordable and does not conflict with the religion, beliefs and culture of the community, to be able to live a healthy, active, and productive life in a sustainable manner. The data source used is secondary data from the Central Statistics Agency (abbreviated BPS). The data consists of monthly per capita expenditure in urban and rural areas by province and group of goods (rupiah) consisting of 33 data records (2011-2018). The group of goods used is expenditures used for food costs. The data mining method used is k-medoids which are part of the clustering. Cluster mapping uses 2 labels namely C1: labels with high food security and C2: labels with low food security. The results of the k-medoids method calculation concluded that 19 provinces were in C1 cluster and 14 provinces were in C2 cluster. From these results it is stated that 42% of Indonesia still has low food security as evidenced by the fulfillment of higher food needs than non-food. These regions are West Sumatra, Riau, Bangka Belitung Islands, Riau islands, DKI Jakarta, West Java, Banten, Bali, Central Kalimantan, South Borneo, East Kalimantan, North Sulawesi, West Papua and Papua.