Explainable Parallel RCNN with Novel Feature Representation for Time Series Forecasting

TL;DR

This paper introduces an explainable parallel RCNN model with a novel shifting feature representation for improved time series forecasting, effectively integrating past data and future covariates while enhancing interpretability.

Contribution

It proposes a new shifting feature representation and a parallel RCNN framework with skip connections, addressing limitations of existing methods in time series forecasting.

Findings

Effective on three datasets, outperforming baselines.

Model interpretability demonstrated via Grad-CAM.

Reduces error accumulation in forecasting.

Abstract

Accurate time series forecasting is a fundamental challenge in data science. It is often affected by external covariates such as weather or human intervention, which in many applications, may be predicted with reasonable accuracy. We refer to them as predicted future covariates. However, existing methods that attempt to predict time series in an iterative manner with autoregressive models end up with exponential error accumulations. Other strategies hat consider the past and future in the encoder and decoder respectively limit themselves by dealing with the historical and future data separately. To address these limitations, a novel feature representation strategy -- shifting -- is proposed to fuse the past data and future covariates such that their interactions can be considered. To extract complex dynamics in time series, we develop a parallel deep learning framework composed of RNN and CNN, both of which are used hierarchically. We also utilize the skip connection technique to improve the model's performance. Extensive experiments on three datasets reveal the effectiveness of our method. Finally, we demonstrate the model interpretability using the Grad-CAM algorithm.