ESTIMATION OF A POSSIBILITY OF PRESERVING ORDER IN A STATE WITH USAGE OF ARTIFICIAL NEURAL NETWORK

Abstract

A political science-mathematical model has been built, designed to assess the possibility of maintaining order in the state. The model is based on a neural network trained on data on the state of many countries in different historical periods. The adequacy of the model is shown by comparing the simulation results with the real course of historical processes. The model was used to estimate the significance of the input parameters. It was found that the most significant parameters that have the greatest impact on the situation in the country are taxes, the state of the economy, and the availability of essential goods. The influence of the most significant parameters on the course of historical events is demonstrated by examples of the situation in France in the period 1629-1634 and in the Ottoman Empire during 1799-1804. Computer experiments were carried out by the scenario forecasting method: using a neural network, calculations were performed by enumerating the values of one parameter, or a small fixed group of parameters, while the values of the other parameters remained unchanged. An attempt has been made to predict the development of the situation in Venezuela for the next five years. A large number of options for forecasts of the development of events were carried out, depending on various combinations of possible measures taken by the government to stabilize the situation. Based on these forecasts, the most effective measures were selected to reduce tensions in the country. The practical value of the study lies in the fact that the created political science and mathematical model can be used to assess the possibility of maintaining order in modern states and to determine the steps necessary to prevent or trigger revolutions, civil wars, etc.