High-Frequency Time Series Prediction Based on Wavelet Transform and ARMA Model

High-frequency time series prediction method based on wavelet transform and ARMA model (WARMA) is proposed. By wavelet decomposition and reconstruction, the original time series is decomposed into an approximate series and several detail series, the reconstructed series is more unitary than the original series in frequency, so it can be predicted with ARMA model. The prediction result of the original series can be obtained by the superposition predicting value of each reconstructed series. Experiment results show that the method gains advantage over the ARMA solely.