The Importance of Forecasting in Industrial Enterprise Management Using Machine Learning

In this work, the assessment of the importance of forecasting in making a management decision during an operational control of an enterprise without including individual cases of dominating impact of forecasted values, including the investing policies and strategic enterprise management, was considered. As an alternative to the expert method, a forecast importance assessment method based on gradient-boosted machine learning algorithm analysis of a decision informational field with the subsequent interpretation of acquired results with Shapley values, allowing for a numerical representation of importance. This method is suggested for use as a tool to increase efficiency of intellectual decision-making support systems by the means of including it in the procedure of automated analysis of importance of features. This work is interdisciplinary, and it concerns problems of systems analysis, economics, and psychology.