A cognitive model for forecasting the stability of the economy under conditions of market uncertainty and risk

Abstract

The article considers the theoretical foundations for predicting the stability of the Russian economy under conditions of market uncertainty and risk using a cognitive model. The relevance of the study lies in the fact that an acute problem in modern conditions is the question of the formation of methodological approaches for a balanced sustainable development of the economy and fi nance. The novelty lies in the fact that the study proposed an approach that involves the use of a cognitive model formed in the GraphViz environment using a semantic frame network in the form of graphs in the DOT programming language. An analysis of the dynamics of both macroeconomic indicators of the real sector of the economy and the parameters of the development of the fi nancial sector of the Russian Federation was carried out. Three perceptron AI models have been developed using the Deductor platform to predict the dynamics of the RF GDP. The criterion for the success of the predictive properties of AI models was the value of the average forecast error. The comparison was carried out every time, cycle by cycle, with the exclusion from the model of factors that have a weak relationship with the effective indicator — the forecast value of GDP and subsequent replacement with another one that has a higher value of the correlation coeffi cient. In addition, within the cycle, if necessary, the hyperparameters of the model can be changed: the number of hidden layers, the number of nodes on the input and hidden layers. In the proposed neural network, the architecture assume s, in addition to the input layer, the use of two hidden layers and an output layer with one parameter. However, in the experiment, the hyperparameters of the neural networks did not change. Neural networks showed high prediction accuracy.