AIThis post was created with the assistance of artificial intelligence (AI).

TL;DR

Czech National Bank Governor Aleš Michl said an AI-assisted model forecasts current-quarter GDP about as well as economists’ forecasts. The bank combines machine learning with a weekly index of fast-moving data, but the speech did not provide model-performance figures or details of the comparison.

The Czech National Bank uses artificial intelligence to help forecast GDP and inflation, Governor Aleš Michl said in a speech at Kyoto University on Nov. 13. He said the bank’s forecast for current-quarter GDP performs about as well as economists’ forecasts, describing an approach that combines machine learning with more frequent indicators of economic activity.

Buying for a business?Offer from Amazon

Get business pricing on office and shipping supplies

  • Business-only prices and quantity discounts
  • Tax-exempt purchasing
  • Multiple users, one account, clear invoices
As an affiliate, we earn on qualifying purchases.

Michl said the bank developed a weekly index of fast-moving data after the COVID-19 pandemic disrupted the availability and timeliness of conventional economic statistics. The indicators he named included electricity consumption and highway truck traffic, which can provide signals about activity before standard GDP estimates are available.

The bank added machine learning in 2023, he said. The model is used for short-term projections, including estimates of GDP in the current quarter. Michl did not describe the model’s specific design, identify the economists’ forecasts used for comparison or give numerical accuracy results in the material provided.

The governor also said the central bank uses AI to forecast inflation. Its broader approach to AI combines tools run on the bank’s own servers, including open-source models for sensitive information, with cloud-based services. Michl said staff follow rules governing which data can be sent to the cloud and which must remain in-house.

At a glance
reportWhen: Speech delivered November 13, 2026; rep…
The developmentAleš Michl told Kyoto University that the Czech National Bank uses AI to forecast GDP and inflation, and that its current-quarter GDP forecast performs about as well as economists’ forecasts.

Faster Signals for GDP Forecasts

GDP figures are released after the economic activity they measure has taken place, and initial estimates can later be revised. A forecast using weekly indicators could give policymakers a more timely read on the economy while they make decisions, including those involving interest rates. The speech describes a forecasting tool, not a replacement for official GDP statistics or a guarantee that its estimates will prove accurate.

Michl’s comparison with economists is relevant because forecasters and central banks depend on timely estimates when current conditions are changing. But the statement, as presented, is a qualitative claim: without a stated evaluation period, benchmark or error measure, readers cannot determine how close the forecasts were or whether the model performed better in some periods than others.

The bank’s account also shows how central banks may use AI within existing forecasting work. The system draws on alternative data and machine learning, while the bank’s stated rules for sensitive information address a separate operational concern: how to use AI tools without exposing protected data.

Products Worth Considering

Logitech MX Mechanical Mini for Mac Wireless Keyboard, Space Gray

Logitech MX Mechanical Mini for Mac Wireless Keyboard, Space Gray

Logitech MX Mechanical Wireless Illuminated Keyboard, Tactile Quiet, Graphite

Logitech MX Mechanical Wireless Illuminated Keyboard, Tactile Quiet, Graphite

Canon SELPHY CP1500 Compact Photo Printer Kit with 2x KP-108IN Ink and Paper Sets

Canon SELPHY CP1500 Compact Photo Printer Kit with 2x KP-108IN Ink and Paper Sets

As an affiliate, we earn on qualifying purchases.

From Pandemic Data to Machine Learning

Michl traced the short-term GDP approach to the pandemic, when conventional data were delayed or less clear. Electricity use and truck traffic offered more frequent observations that could help the bank estimate economic activity between official releases. The bank built a weekly index from such indicators, then added machine learning in 2023, according to the governor.

The remarks appeared in a lecture at Kyoto University in Kyoto, delivered Nov. 13 and published by the Bank for International Settlements on Nov. 19. Michl’s discussion of AI formed part of a broader account of the Czech National Bank’s technology and operations. The source gives no further breakdown of the GDP model’s inputs, forecasting process or record.

How the Forecast Comparison Was Measured

The speech does not state how forecast performance was measured, which economists’ projections were used as a benchmark, or what time period the comparison covered. It also provides no error rates, forecast history or results showing how the model performs during different economic conditions. Without those details, the claim that the AI-assisted forecast performs about as well as economists’ forecasts cannot be independently assessed from the speech alone.

Michl did not specify which indicators, beyond electricity consumption and truck traffic, currently enter the model, how much each contributes, or whether the bank uses the same method for all GDP estimates. The source also does not say whether the model’s forecasts are published separately or how they are combined with staff judgment and other forecasting methods.

Further Model Details to Watch

The speech did not announce a new forecast, a change to the central bank’s monetary policy or a release date for additional technical information. The next useful evidence would be published validation results showing the model’s forecasting errors over a defined period and comparing them with named economist or institutional forecasts.

Until the bank provides those details, Michl’s remarks establish that the Czech National Bank uses machine learning and faster-moving data for short-term GDP projections, and that its governor considers the results comparable to economists’ forecasts. The scale and consistency of that performance remain unreported in the source material.

Key Questions

What did the Czech National Bank say about AI and GDP forecasts?

Governor Aleš Michl said the bank uses AI to forecast GDP and that its current-quarter estimate performs about as well as economists’ forecasts. The speech did not include numerical accuracy results.

What data does the bank use for its short-term GDP forecasts?

Michl cited electricity consumption and highway truck traffic as examples of fast-moving indicators used to build a weekly activity index. The speech did not provide a full list of model inputs.

When did the Czech National Bank add machine learning?

Michl said the bank added machine learning in 2023, building on short-term forecasting work that began during the COVID-19 pandemic.

Does the speech prove AI forecasts GDP better than economists?

No. Michl described the result as about as good as economists’ forecasts, not better. The speech did not specify the comparison method, time period or forecast-error figures.

Source: bis.org

This content is for general information only and is not financial, tax or legal advice. Consult a qualified professional for decisions about your money.
You May Also Like

Brad And Noah Discuss The Reindustrialization Of America

Brad DeLong and Noah Smith discuss security, growth and jobs as reasons to rebuild U.S. manufacturing—and the barriers they say remain.

UT Austin Police Share Details On Speedway Medical Emergency Response

An IdeaNavigator AI brief says UT Austin police identified activity on Speedway as a medical emergency response, but provides few incident details.

Why Escalation Quality Shapes Business Speed

Great escalation quality can significantly boost business speed, but understanding how to refine these protocols is key to unlocking faster resolutions.

Today In AI And Work: A November 14, 2026 Update

A Nov. 14 AI-and-work roundup tracks financial risk, robot models, an Uber vendor breach and the FAA outage, with key facts and open questions.