Investigation of computational intelligence methods in forecasting problems at stock exchanges

In this paper, the forecasting problem of share prices at New York Stock Exchange (NYSE) was considered and investigated. For its solution alternative methods computational intelligence were suggested investigated: LSTM networks, GRU, simple recurrent neural networks (RNN) Group Method Data Handling (GMDH). The experimental investigations intelligent for CISCO carried out efficiency estimated compared. It established that method GMDH had best accuracy compared to other in forecasting.