Neural Network Technology of the Financial and Economic Model Synthesis of Production as the Fragment of the Economy Digitalization = Нейросетевая технология синтеза финансово-экономической модели производства как фрагмент цифровизации экономики

Abstract

The purpose of the article is to develop a technology for desgning neural network models for automatic monitoring of the tax burden to achieve the optimal balance between the possibility of developing a successful business and sufficient filling of the regional budget. A multi-layer perceptron and a back-propagation algorithm were applied for the research as well as a neural control technology. The automation of the process of determining the elements of the gradient vector was produced in implementing traditional method of the backpropagation of error by using neural control technology. For the first time, a solution to optimize the fiscally-tax burden (FTB) of the region has proposed with the application of the back-propagation algorithm. Using the proposed methodology a software tool will be created for the transition to an automatic system for optimal management of the economy.

Метою статті є розробка технології для моделювання нейронних мережевих моделей для автоматичного моніторингу податкового навантаження для досягнення оптимального балансу між можливістю розвитку успішного бізнесу та достатнім наповненням обласного бюджету.