Using payments data to nowcast macroeconomic variables during the onset of Covid-19

Abstract

The COVID-19 pandemic and the resulting public health mitigation have caused large-scale economic disruptions globally. During this time, there is an increased need to predict the macroeconomy's short-term dynamics to ensure the effective implementation of fiscal and monetary policy. However, economic prediction during a crisis is challenging because of the unprecedented economic impact, which increases the unreliability of traditionally used linear models that use lagged data. We help address these challenges by using timely retail payments system data in linear and nonlinear machine learning models. We find that compared to a benchmark, our model has a roughly 15 to 45% reduction in Root Mean Square Error when used for macroeconomic nowcasting during the global financial crisis. For nowcasting during the COVID-19 shock, our model predictions are much closer to the official estimates.

Macroeconomic Predictions using Payments Data and Machine Learning

“…In modern economies, this is accomplished via centralized payments systems. The data coming from such systems are potentially useful because they are (a) timely, i.e., available immediately after the end of each period, (b) available at high-frequency, i.e., at the transaction or day levels, (c) precise, i.e., carry no sampling or measurement error, and (d) comprehensive, i.e., capture a broad range of financial activities across the country (Galbraith and Tkacz 2007;Chapman and Desai 2020).…”

“…To exploit non-traditional and large-scale data sources, researchers have recently begun utilizing ML models for economic nowcasting (Richardson et al 2020;Maehashi and Shintani 2020;Chapman and Desai 2020). ML models have been shown to handle wide-and large-scale data efficiently and can manage collinearity.…”

“…1 ML models could prove useful in efficiently handling a wide variety of payments data and effectively managing collinearity in such data. This is beneficial because some of the payment streams used here are strongly correlated with each other (Chapman and Desai 2020). ML models can also help capture sudden, large, and possibly nonlinear effects of economic crises and the impact of unconventional policies designed to alleviate them (Vrontos et al 2020;Coulombe et al 2021).…”

“…econometricians have begun using ML models for macroeconomic nowcasting (Chakraborty and Joseph 2017;Richardson et al 2020;Maehashi and Shintani 2020;Chapman and Desai 2020). The cited articles suggest that ML models complement traditional econometric tools and are useful in extracting economic value from non-traditional data sources.…”

Official Statistics in the Wake of the Covid-19 Pandemic: A Central Banking Perspective

“…In a large number of countries, this was done by using "traditional" but secon- duction of steel, etc). 5 A particularly interesting opportunity was provided by national payment system high-frequency data that are often available easily and immediately for central banks (because of their specific mandates) and that could be used to shed light on macroeconomic developments (Chapman & Desai, 2021).…”