Modelling Efficient Military Deployments with Machine Learning -- K-Means Clustering in R

Armed forces in Latin America & the Caribbean are faced with the challenge of having to operate with a multi-dimensional mandate. In times of heightened civil unrest they are required to undertake peace-keeping operations, gang warfare driven by the arms-for-drugs trade calls for counter-insurgence style deployments and seasonal natural disasters often require their services to support the essential services under extreme conditions. With limited resources, every opportunity to prevent the unnecessary expenditure while maintaining effectiveness needs to be taken. In this post I will demonstrate how the application of the K-means clustering algorithm, in the context of how Naval Forces in Latin America and the Caribbean, can be used to schedule efficient Naval deployments and reduce the number of unnecessary operations. For this example I simulated 200 data points that represent the location of incidents that would result in the need for Naval resources to be deployed in the Caribbean Sea. The data have a timestamp that indicates the time of day of each incident on a 24-hour clock cycle.