Explainable Prediction of Economic Time Series Using IMFs and Neural Networks

TL;DR

This paper explores how decomposing economic time series into IMFs and analyzing them with neural networks improves prediction interpretability and performance, revealing the significance of long-term trends and the impact of model architecture.

Contribution

It introduces a method combining IMFs and DeepSHAP for interpretable economic time series prediction with neural networks, highlighting the importance of long-term IMFs.

Findings

Long-term IMFs are most influential in predictions.

Removing high-frequency IMFs can improve model accuracy.

LSTM distributes importance more evenly across IMFs.

Abstract

This study investigates the contribution of Intrinsic Mode Functions (IMFs) derived from economic time series to the predictive performance of neural network models, specifically Multilayer Perceptrons (MLP) and Long Short-Term Memory (LSTM) networks. To enhance interpretability, DeepSHAP is applied, which estimates the marginal contribution of each IMF while keeping the rest of the series intact. Results show that the last IMFs, representing long-term trends, are generally the most influential according to DeepSHAP, whereas high-frequency IMFs contribute less and may even introduce noise, as evidenced by improved metrics upon their removal. Differences between MLP and LSTM highlight the effect of model architecture on feature relevance distribution, with LSTM allocating importance more evenly across IMFs.