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

James Chapman and Ajit Desai

Abstract

The Covid-19 pandemic and its resulting public health mitigation measures have caused large-scale economic disruption globally. At 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 of such an event, which increases the unreliability of traditionally used linear models that employ lagged data. We help to address these challenges by using timely retail payments system data in linear and nonlinear machine learning models. We find that, compared with a benchmark, our model has a roughly 15–45% 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.