Exponent back propagation neural network forecasting for financial cross-correlation relationship

• A new neural network (EBPNN) is developed.
• An approach to cross-correlations prediction between financial time series.
• Empirical research is performed in testing the forecasting effect of EBPNN.
• Forecasting long-term cross-correlations by training short-term cross-correlations.
• The proposed model is advantageous in increasing the forecasting precision.

An improved neural network is developed to predict the cross-correlations between two financial time series. In order to capture the large fluctuations of data set, an exponent back propagation neural network (EBPNN) is introduced in the present work, which information is not only processed locally in each neural unit by computing the dot product between its input vector and its weight vector, but also processed by adding the dot product between its exponential type function of the input vector and its corresponding new weight vector. The proposed prediction model improves the activation function of the neural network, and makes an approach on cross-correlations forecasting with the particular input and output variables. The empirical research is performed in testing the forecasting effect of the EBPNN model and a comparison to back propagation neural network (BPNN). The empirical results show that the EBPNN is advantageous in increasing the predicting precision.