The object of the research is the forecasting processes of financial instruments in stock markets in the face of uncertainty. A high degree of uncertainty in the stock markets significantly complicates the process of forecasting the dynamics of financial instruments. This problem matters both for states and for investment companies. As well as for other market participants who need to make long-term investment decisions based on preventive measures to reduce the impact of the risks of financial crises on their activities. In this paper, the authors analyze a number of prognostic models used in the field of numerical series calculations. In the context of forecasting prices on stock markets, the strengths and weaknesses of popular models in practice are identified. Their mathematical functions are presented, calculation algorithms are explained, and author's conclusions are given on the degree of effectiveness of the application of individual models in the field of financial instruments.In the course of the study, the authors studied a number of different scientific works on this problem and analyzed the obtained information. The result of the analysis shows that decision-making processes in forecasting changes in financial instruments will be complicated by the presence of external factors, but also these external factors are the result of the activities of individual market participants. This is due to the fact that when forecasting financial instruments in the stock markets, pseudo-random environmental events can be leveled. Many existing forecasting solutions allow low accuracy in forecasting modeling, so it is more rational to use multi-agent technologies. Thanks to them, greater accuracy of indicators is ensured, in comparison with similar methods, such as econometric models (the most famous of which are: ARCH, GARCH, VAR).The research results obtained in this work can be used to predict financial crises, as well as to develop methods to counter them.