Macroeconomic predictions using payments data and machine learning

Arbeitspapier

Predicting the economy's short-term dynamics-a vital input to economic agents' decisionmaking process-often uses lagged indicators in linear models. This is typically sufficient during normal times but could prove inadequate during crisis periods such as COVID-19. This paper demonstrates: (a) that payments systems data which capture a variety of economic transactions can assist in estimating the state of the economy in real time and (b) that machine learning can provide a set of econometric tools to effectively handle a wide variety in payments data and capture sudden and large effects from a crisis. Further, we mitigate the interpretability and overfitting challenges of machine learning models by using the Shapley value-based approach to quantify the marginal contribution of payments data and by devising a novel cross-validation strategy tailored to macroeconomic prediction models.

Object Details

• Language: Englisch

References and Relationships

• Bibliographic citation: Series: Bank of Canada Staff Working Paper ; No. 2022-10

Classification and Topics

• Classification: Wirtschaft ; Forecasting Models; Simulation Methods ; Large Data Sets: Modeling and Analysis ; Prices, Business Fluctuations, and Cycles: Forecasting and Simulation: Models and Applications ; Monetary Systems; Standards; Regimes; Government and the Monetary System; Payment Systems ; Monetary Policy
• Subject: Econometric and statistical methods ; Business fluctuations and cycles ; Payment clearingand settlement systems

Contributors, Places and Time

• Event: Geistige Schöpfung
• (who): Chapman, James ; Desai, Ajit
• Event: Veröffentlichung
• (who): Bank of Canada
• (where): Ottawa
• (when): 2022

Further information

• DOI: doi:10.34989/swp-2022-10
• Handle: http://hdl.handle.net/10419/261263
• Last update: 10.03.2025, 11:43 AM CET