Pavlyshenko P. Methods of intellectual analysis of consolidated data for decision-making support

The thesis focuses on the development of methods of modeling, formation of analytical features, intellectual analysis of tabular and textual consolidated data for increasing the accuracy, reliability and self-descriptiveness of the analysis results, which are used to support decision-making in information and analytical systems. A method for optimizing the predictive analytics of time series using stacking combination and a selection of different types of models based on linear regression LASSO and Bayesian regression has been developed. A combination of Bayesian, linear and machine-learning logistic regression in a problem of detecting technical failures has been analyzed. The optimization of the sequence of actions of an intelligent agent in the tasks of demand analytics u sing deep Q-learning and simulation modeling of the interaction environment has been considered. A model of vector representation of textual data in the space of semantic and thematic fields has been proposed. An analysis of textual data based on machine learning algorithms using quantitative features of semantic and thematic fields has been carried out. A method for identifying additional analytical features based on lexeme combinations in the semantic structures of text arrays has been developed. A model of semantic concepts of text based on the theory of formal concepts analysis has been proposed.