WEITS: A Wavelet-enhanced residual framework for interpretable time series forecasting

TL;DR

WEITS is a novel wavelet-enhanced residual deep learning framework that offers interpretable, efficient, and high-performing time series forecasting by integrating frequency analysis with residual architecture.

Contribution

It introduces a frequency-aware deep learning framework with wavelet decomposition and residual architecture, enhancing interpretability and efficiency in time series forecasting.

Findings

Competitive forecasting performance on real-world datasets

High computational efficiency compared to existing methods

Seamless integration with state-of-the-art approaches

Abstract

Time series (TS) forecasting has been an unprecedentedly popular problem in recent years, with ubiquitous applications in both scientific and business fields. Various approaches have been introduced to time series analysis, including both statistical approaches and deep neural networks. Although neural network approaches have illustrated stronger ability of representation than statistical methods, they struggle to provide sufficient interpretablility, and can be too complicated to optimize. In this paper, we present WEITS, a frequency-aware deep learning framework that is highly interpretable and computationally efficient. Through multi-level wavelet decomposition, WEITS novelly infuses frequency analysis into a highly deep learning framework. Combined with a forward-backward residual architecture, it enjoys both high representation capability and statistical interpretability. Extensive experiments on real-world datasets have demonstrated competitive performance of our model, along with its additional advantage of high computation efficiency. Furthermore, WEITS provides a general framework that can always seamlessly integrate with state-of-the-art approaches for time series forecast.