Central banks complement traditional models with AI
Time series and semi-structural models remain economists’ choices for forecasting
The majority of central banks use traditional modelling tools for macroeconomic analysis, but most economics departments now complement the tools with machine learning/artificial intelligence, the Economics Benchmarks 2026 reveal.
For this benchmark, larger central banks are respondents with over the median workforce of 795 officials. Sixteen central banks fall in this category, while 15 others make up smaller central banks.
Four-fifths of larger central banks indicated they make use of AI for
Only users who have a paid subscription or are part of a corporate subscription are able to print or copy content.
To access these options, along with all other subscription benefits, please contact info@centralbanking.com or view our subscription options here: www.centralbanking.com/subscriptions
You are currently unable to print this content. Please contact info@centralbanking.com to find out more.
You are currently unable to copy this content. Please contact info@centralbanking.com to find out more.
Copyright Infopro Digital Limited. All rights reserved.
As outlined in our terms and conditions, https://www.infopro-digital.com/terms-and-conditions/subscriptions/ (point 2.4), printing is limited to a single copy.
If you would like to purchase additional rights please email info@centralbanking.com
Copyright Infopro Digital Limited. All rights reserved.
You may share this content using our article tools. As outlined in our terms and conditions, https://www.infopro-digital.com/terms-and-conditions/subscriptions/ (clause 2.4), an Authorised User may only make one copy of the materials for their own personal use. You must also comply with the restrictions in clause 2.5.
If you would like to purchase additional rights please email info@centralbanking.com
More on Economics
Economics departments use multiple coding languages
More than half of central banks use five or more coding languages and tools
Geopolitics is fastest-rising research topic for economists
Research economists are most widely judged on their output of papers
Economists devote up to half of working hours to research
Higher-paid research economists tend to spend more time on own research
Dedicated data units widely used in economics departments
Teams make use of varied microdata in their work
Central banks predict growth more accurately than inflation
AI models may offer more precise forecasts
AI impact and usage growing in central bank economics departments
Regional variation exists, but adoption is increasing across the board
Most key projection models capture policy rates
But respondents rarely disclose policy rate forecasts alongside scenarios
Third of key models now employ endogenous financial sector
Multiple channels of monetary transmission rooted in majority models