We combine convolutional neural network (CNN) and gated recurrent unit (GRU) to form a new structure and embed it as a base layer in the autoencoder (AE) framework to efficiently extract features from financial time series data. To better utilize the hierarchical features, skip connection is...

This paper models the return series of USD/CNY exchange rate by considering the conditional mean and conditional volatility simultaneously. An index type functional-coefficient model is adopted to model the conditional mean part and a GARCH type model with a policy dummy variable is applied to...