DeLELSTM: Decomposition-based Linear Explainable LSTM to Capture Instantaneous and Long-term Effects in Time Series

TL;DR

DeLELSTM is an interpretable LSTM model that decomposes time series influences into instantaneous and long-term effects, enhancing transparency while maintaining competitive forecasting accuracy.

Contribution

This paper introduces DeLELSTM, a novel LSTM architecture that explicitly separates and explains instantaneous and long-term effects of variables in time series forecasting.

Findings

DeLELSTM achieves competitive forecasting performance.

The model provides clear, interpretable explanations of variable influences.

Effective on multiple real-world datasets.

Abstract

Time series forecasting is prevalent in various real-world applications. Despite the promising results of deep learning models in time series forecasting, especially the Recurrent Neural Networks (RNNs), the explanations of time series models, which are critical in high-stakes applications, have received little attention. In this paper, we propose a Decomposition-based Linear Explainable LSTM (DeLELSTM) to improve the interpretability of LSTM. Conventionally, the interpretability of RNNs only concentrates on the variable importance and time importance. We additionally distinguish between the instantaneous influence of new coming data and the long-term effects of historical data. Specifically, DeLELSTM consists of two components, i.e., standard LSTM and tensorized LSTM. The tensorized LSTM assigns each variable with a unique hidden state making up a matrix $\mathbf{h}_t$, and the standard LSTM models all the variables with a shared hidden state $\mathbf{H}_t$. By decomposing the $\mathbf{H}_t$ into the linear combination of past information $\mathbf{h}_{t-1}$ and the fresh information $\mathbf{h}_{t}-\mathbf{h}_{t-1}$, we can get the instantaneous influence and the long-term effect of each variable. In addition, the advantage of linear regression also makes the explanation transparent and clear. We demonstrate the effectiveness and interpretability of DeLELSTM on three empirical datasets. Extensive experiments show that the proposed method achieves competitive performance against the baseline methods and provides a reliable explanation relative to domain knowledge.