Purpose. Development and construction of economic-mathematical forecasting model of exchange rates by means of neural networks for definition of exchange rates behavior on the Internet market taking into account factors of technical and fundamental analyses. Methodology. For solution of this goal methods of the comparative analysis, systematic comprehensive approach and methods of economic-mathematical modeling by means of neural networks were used. Findings. Research of major factors by tools available to do a forecast concerning fluctuations of exchange rates in the future was carried out. We have defined that the exchange rates behavior is influenced by rather large number of factors relating to methods of fundamental and technical analyses. It was established that any factors cannot guarantee 100 % reliability in a forecast. Only application of a comprehensive approach insures high degree of forecast accuracy. Economic-mathematical forecasting model of exchange rates with the neural networks for the purpose of implementation of a comprehensive approach was offered and constructed. It has allowed complex indicators of fundamental and technical analyses. On the basis of technical and fundamental analyses indicators of exchange rates behavior on the Internet market the group of factors which have numerical measurement was created. Justification of mathematical apparatus of neural networks as optimum for construction economic-mathematical model for the performance of forecasts and taking into account the purpose put in this work was executed. On the basis of the created group of factors construction of economy was executed - mathematical model of funds of neural networks, for which entrance data on the selected factors move and on exit look-ahead value of exchange rates turns out. Originality. Construction of economic-mathematical forecasting model of exchange rates for Internet market was executed by neural networks which unlike the existing considering groups of ten factors, such as: the index of the relative size of the prices, the index of simplification of the market, the index of Dow Jones, the "Standard and powers" index, the New York stock exchange index, indices of the American stock exchange, the RSI indicator, the average index of the directed movement ADX, the index of off-exchange turn, the stochastic indicator. Practical value. The practical significance of these results is the possibility of increasing the accuracy of the forecast of exchange rates on the Internet market by the use of advanced mathematical apparatus, which was based on the expanded set of factors affecting the fluctuations of exchange rates.

  Повний текст PDF - 134.923 Kb    Зміст випуску     Цитування публікації

  Якщо, ви не знайшли інформацію про автора(ів) публікації, маєте бажання виправити або відобразити більш докладну інформацію про науковців України запрошуємо заповнити "Анкету науковця"