Decision support system for the machine learning methods selection in big data mining

Abstract

This article focuses on the aspects of the decision support system for the machine learning methods selection in big data mining development. The paper includes the results of the analysis of the problem of intellectual processing and analysis of big data. It describes proposal ways of using metadata as a basis for the formation of an analytical rating for evaluating machine learning methods. The paper presents the results of designing and using a decision support system for evaluating machine learning methods for solving data mining problems. The developed decision support system allows us to reduce the analysis time of suitable methods for solving machine learning problems by a data science analyst, taking into account the specifics of the input data arrays, their volumes, structure and other metadata.