Application of wavelet decomposition in time-series forecasting

- Wavelet-based multiresolution decomposes a time series into a set of constitutive series with an explicitly defined hierarchical structure.
- We show that this decomposition method can improve the accuracy of forecasts of original times series data.

Observed time series data can exhibit different components, such as trends, seasonality, and jumps, which are characterized by different coefficients in their respective data generating processes. Therefore, fitting a given time series model to aggregated data can be time consuming and may lead to a loss of forecasting accuracy. In this paper, coefficients for variable components in estimations are generated based on wavelet-based multiresolution analyses. Thus, the accuracy of forecasts based on aggregate data should be improved because the constraint of equality among the model coefficients for all data components is relaxed.