Output details

Non-stationary and stationary prediction of financial time series using dynamic ridge polynomial neural network

<24> The work describes an efficient predictor structure for financial time series prediction based on a new type of a recurrent polynomial neural network, which exploits correlations between input data and the temporal dynamics of the financial time series. The proposed neural network was shown to be a powerful predictor, by making use of multi-linear interactions, and demonstrated advantages in capturing chaotic movement in the financial signals with an improvement in the profit return and rapid convergence.