Neural networks have proven to be highly adaptable to various tasks associat-ed with large data sets and their processing in order to obtain new knowledge and data for subsequent planning of the development of various systems. Neural networks are used not only in the processing of large data sets, but also in the construction of predictive models. In this article, we built a neural net-work model for calculating and forecasting profit index of the agro-industrial complex (AIC) of Russia, on the basis of aggregated input factor parameters, reflecting the potential of the industries. In addition to the neural network forecast, the article builds a profit forecast using the method of regres-sion-correlation analysis, which has long been used by economists. For fore-casting purposes, the analysis of the dynamics of development of the branches of agro-industrial complex was carried out and the main factors determining their future opportunities were selected. Using the online platform Deductor Studio Academic assessed the dependence and impact of input indicators on the derived profit indicator and checking the correlation coefficients between the parameters were calculated. The obtained forecasted profit values were com-pared with the actual profit value and the difference in the accuracy of the forecasts was calculated.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.