Reservoir Computing for Macroeconomic Forecasting with Mixed Frequency Data

TL;DR

This paper introduces the Multi-Frequency Echo State Network (MFESN), a reservoir computing approach for macroeconomic forecasting with mixed frequency data, outperforming traditional methods in efficiency and accuracy.

Contribution

The paper presents MFESN, a novel reservoir computing framework that efficiently models mixed frequency macroeconomic data, outperforming MIDAS and DFM in forecasting accuracy and computational cost.

Findings

MFESN achieves superior forecasting accuracy compared to MIDAS and DFM.

MFESN is more computationally efficient than traditional models.

The approach effectively incorporates many series with mixed frequencies.

Abstract

Macroeconomic forecasting has recently started embracing techniques that can deal with large-scale datasets and series with unequal release periods. MIxed-DAta Sampling (MIDAS) and Dynamic Factor Models (DFM) are the two main state-of-the-art approaches that allow modeling series with non-homogeneous frequencies. We introduce a new framework called the Multi-Frequency Echo State Network (MFESN) based on a relatively novel machine learning paradigm called reservoir computing. Echo State Networks (ESN) are recurrent neural networks formulated as nonlinear state-space systems with random state coefficients where only the observation map is subject to estimation. MFESNs are considerably more efficient than DFMs and allow for incorporating many series, as opposed to MIDAS models, which are prone to the curse of dimensionality. All methods are compared in extensive multistep forecasting exercises targeting US GDP growth. We find that our MFESN models achieve superior or comparable performance over MIDAS and DFMs at a much lower computational cost.