Assessment of Financial Stability of a Partner Organization Using Dl Random Forest, Var, Z-Altman, Hurwitz Models in Conditions of Turbulent Economy

Abstract

The article discusses the issues of forecasting profits and assessing the fi nancial stability of an enterprise in the confectionery industry — the Confil company. Assessing a company as a strategic partner using models such as the deep learning model "Random Forest" (DL Random Forest), VaR, "Z-Altman", Hurwitz matrix in modern conditions has practical signifi cance. The relevance of the study lies in the fact that in a turbulent economy, approaches to ensuring the sustainable development of an organization based on artificial intelligence are increasingly being used. The scientific novelty lies in the fact that the study used a set of models that made it possible to make a decision regarding the choice of an enterprise as a strategic partner for business. In particular, a deep learning model DL model "Random Forest" was formed, which makes it possible to obtain a forecast of the company’s net profi t. The parameters included in the DL model were assessed, paired correlation coeffi cients were calculated, which made it possible to assess the strength and direction of the factors infl uencing the amount of net profi t. The VaR model made it possible to calculate an alternative forecast of net profi t and obtain an assessment of the company’s fi nancial risk; the "Z-Altman" model made it possible to assess the risk of bankruptcy of the enterprise. In addition, using the calculated multiple regression coeffi cients, the Hurwitz matrix was formed and a positive value of the matrix determinant was obtained, which made it possible to draw a conclusion about the sustainability of the enterprise as a system. The practical significance of the study is determined by the possibility of using its results in practice, in particular, in the formation of a sustainable development strategy for an enterprise.