Problems threatening food security are reduced agricultural land and decreased production caused by climate change. In 2 years, the rice harvested area in Indonesia has decreased by around 6.33%. This research aims to know how food security is in Indonesia.The secondary data is then processed using the Microsoft Excel application and analyzed using Machine Learning in Rstudio. Several variables were examined, Population, Area of Harvested Land, Productivity of Rice Commodity, and Level of Disaster Risk. Based on the literature, a food security ratio is calculated to get the index that will explain the deficit or surplus of food availability.This research shows that the model has an accuracy rate of 93.4%. Strengthening the results given by the elbow method, the gap statistical method ensures that the optimal number of clusters recommended by machine learning is k2, so the next process is to group districts/cities into 2 (two) clusters.a model can be formed that can be used to predict the condition of food security fairly accurately (accuracy level 90%). Cities in Indonesia when clustered based on this research can optimally be divided into two clusters which show the deficit and surplus of food.