Reservoir Computing for Macroeconomic Forecasting with Mixed Frequency Data
arXiv:2211.00363 · doi:10.1016/j.ijforecast.2023.10.009
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.
76 pages, 28 figures, appendices included
References in corpus (8)
- Using Machine Learning to Replicate Chaotic Attractors and Calculate Lyapunov Exponents from Data
- Echo State Networks trained by Tikhonov least squares are L2(μ) approximators of ergodic dynamical systems
- Using Data Assimilation to Train a Hybrid Forecast System that Combines Machine-Learning and Knowledge-Based Components
- Learning strange attractors with reservoir systems
- Memory and forecasting capacities of nonlinear recurrent networks
- Risk bounds for reservoir computing
- Transport in reservoir computing
- Memory of recurrent networks: Do we compute it right?