The financial time series forecasting based on proposed ARMA-GRNN model

Autoregressive moving average (ARMA) was one of the popular linear models in financial time series forecasting in the past. Generalized regression neural network (GRNN) is a branch of RBF neural network. Recent research activities in forecasting with GRNN suggest that GRNN can be a promising alternative to the traditional time series model. It has shown great ability in modeling and forecasting nonlinear time series. This paper proposes an ARMA-GRNN model that combines ARMA and GRNN models. The combined model is proposed to make use of the advantage of ARMA and GRNN models in linear and nonlinear modeling. And ARMA model aids in improving the combined model performance by capturing statistical information of the time series. The relative tests testify that the combined model can be an effective way to improve forecasting accuracy achieved by either of the models used separately.