Information technologies for solving problems of grouping objects based on cluster analysis methods

Abstract

The article examines the approaches of using information technologies for grouping objects based on the use of cluster analysis methods. Based on Data Mining mining tools, approaches for cluster analysis are considered. The main methods of cluster analysis are considered. For example, the demand for goods in shopping centers is considered and an analysis of customer preferences is carried out. Clustering of objects was carried out on a sufficiently large set of data (transactions) using the Deductor Studio tool. It is shown that for clustering objects with an unknown number of classes, the g-means method is the most preferable. Clusters with the most popular sets have been identified.