Subset selection variables of the model using AI libraries

Abstract

Investments in IT structures of companies resulted in an unprecedented increase in the collected data. This enormous increase in data collected in practically every aspect of the sphere of life has led to an increased interest in the methods of extracting information, knowledge and dependencies. When thinking about data analytics, you should almost always select the data so that each model in its final form reflects the process under study as accurately as possible. In this article, the most common methods of selecting variables for the model will be presented. This process is one of the stages of model building and the final effect of the model to a large extent depends on its course.