Algorithm of finding optimal location for distribution centers for order delivery by using unsupervised machine learning methods

The problem of automating the finding of centers of mass for a system of objects on the Earth's surface is considered. This task often arises, for example, in the course of optimizing the logistics network of the company in quickening the order delivery to the customers. Automation of this process contributes to the optimization of the staff involved, improves the quality of decisions on the development of logistics networks by estimating the situation based on data. The authors of the article suggest to use the modified metric K-means machine learning algorithm for determining the optimal locations of distribution centers of the delivery of goods to settlements. Such centers can significantly reduce transportation costs, as well as provide a high level of customer service quality. The research is also touches upon the more complicated cases of using the chosen method for finding warehouse locations, since the process depends on the logistics strategy of the company. The data were analyzed and a set of features suitable for the clustering algorithm as weights was determined. The data were processed and transformed to apply the algorithm. There has been developed a class for finding distances between points on the highways. The optimal number of clusters is calculated. The clustering algorithm has been modified in terms of calculating distances between objects. With the modified algorithm, a set of candidate points for the location of distribution centers was obtained.