5 February 2021
Dr Sophie van Huellen, Lecturer in Economics at SOAS, has been awarded a grant from UKRI, jointly with colleagues from University College London (UCL), University of St Gallen, and Konstanz University. The project, with title Reservoir Computing for Macroeconomic Modelling, brings together an interdisciplinary and cross-sector research team of economists, statisticians, mathematicians, data scientists, and economic practitioners to explore the application of new techniques in machine learning to macroeconomic modelling and forecasting.
With the increased globalisation of financial markets, financial crises and shocks have become more frequent and contagious. Despite a mass of data on financial markets and the banking sector being available, traditional macroeconomic models account for financial influences primarily through monetary aggregates and interest rates. This narrow representation of financial markets is proving increasingly inadequate.
A major weakness in the existing models is the absence of aggregate variables which can adequately represent broad financial market conditions. This absence has stimulated a growing literature on the construction of aggregate financial conditions indices (FCIs) formed from a large set of financial variables by use of dynamic factor models. However, such FCIs do not perform well if the number of financial variables considered becomes large and have difficulties taking country-specific characteristics into account.
The project suggests applying new techniques in machine learning, namely reservoir computing, instead. Reservoir computing is a relatively recent approach to machine learning and has not been applied to macroeconomic modelling yet. The technique is particularly promising as it can deal with a mix of time series data and unstructured data, handle frequency mismatch and high dimensionality of input data well, and provides interpretable results, a key condition from an economic modelling perspective.