--- title: How IMF mis-forecasts GDP growth date: 2026-06-22T10:41:30+08:00 categories: - data - visualization - llms --- The IMF forecasts GDP growth every year. Their forecasts for the current year are slightly low. Their forecasts for the next year are slightly high. After that, it remains high. ![](https://sanand0.github.io/datastories/imf-gdp-forecast-errors/screenshot.avif) Some forecasts, like [China](https://sanand0.github.io/datastories/imf-gdp-forecast-errors/#country=China), [Singapore](https://sanand0.github.io/datastories/imf-gdp-forecast-errors/#country=Singapore), [UAE](https://sanand0.github.io/datastories/imf-gdp-forecast-errors/#country=United+Arab+Emirates), [Equatorial Guinea](https://sanand0.github.io/datastories/imf-gdp-forecast-errors/#country=Equatorial+Guinea) are consistently low. Other forecasts, like [Japan](https://sanand0.github.io/datastories/imf-gdp-forecast-errors/#country=Japan), [Congo](https://sanand0.github.io/datastories/imf-gdp-forecast-errors/#country=Congo%2C+Democratic+Republic+of+the), [Mexico](https://sanand0.github.io/datastories/imf-gdp-forecast-errors/#country=Mexico), [Pakistan](https://sanand0.github.io/datastories/imf-gdp-forecast-errors/#country=Pakistan) are consistently high. --- The interesting meta-pattern is how this sort of past-forecast analysis can be done for any topic. This emerged from an [Ethan Mollick post](https://bsky.app/profile/emollick.bsky.social/post/3moraa7zius2c) and then I asked: - **Me**: Ethan Mollick had GPT-5.5 Pro update his grad school paper. Cool! What can I do like this? - **[Claude](https://claude.ai/share/a79319c0-96a1-4e18-a2ed-c0911e232875)**: Analyze your past work - like your blog posts. 1. Fact-check it 2. Find wrong sources 3. Critique it 4. Find contradictions 5. Find buried ledes / unbuilt sequels 6. Find what aged badly. What's the pattern? - **Me**: Um, what about others' work? - **[Claude](https://claude.ai/share/a79319c0-96a1-4e18-a2ed-c0911e232875)**: Sure! 1. Check IMF GDP forecast accuracy 2. Check target market size forecasts 3. Check company / asset price forecasts 4. Find which books are based on studies no longer true 5. Find sources of popular stats that are wrong 6. Find what numbers people quietly revised - **Me**: Where can I find IMF GDP forecasts? - **[ChatGPT](https://chatgpt.com/share/6a389d6e-4180-83e8-a759-95734a64b000)**: On the [IMF Data WEO site](https://data.imf.org/en/datasets/IMF.RES%3AWEO) - **Me**: Check IMF GDP forecast accuracy. - **[ChatGPT](https://chatgpt.com/share/6a389d6e-4180-83e8-a759-95734a64b000)**: The IMF has a modest optimistic bias for future-year GDP-growth forecasts, but not for same-year nowcasts. - **Me**: Translate that to English. - **[ChatGPT](https://chatgpt.com/share/6a389d6e-4180-83e8-a759-95734a64b000)**: For the current year, IMF typically underestimates. Next year onwards, they typically overestimate. - **Me**: Why? How? - **[ChatGPT](https://chatgpt.com/share/6a38a70d-4f34-83ee-b193-0b3dd2351422)**: IMF has systematic biases. - Advanced economies are easier to forecast and slightly less biased - Some countries (China, UAE, ...) are largely under-forecasted. Others (DR Congo, Haiti, ...) are consistently over-forecasted. - They underpredicts extremes in both directions. - When their forecast is very high, it is more likely to be too high. - Corrections are timid. They don't close old error gap until very late. - **Me**: Draw this as a dot chart. - **[ChatGPT](https://chatgpt.com/share/6a389d6e-4180-83e8-a759-95734a64b000)**: OK - **Me**: Spread out the dots. - **[ChatGPT](https://chatgpt.com/share/6a389d6e-4180-83e8-a759-95734a64b000)**: OK - **Me**: Let me filter by country. - **[ChatGPT](https://chatgpt.com/share/6a389d6e-4180-83e8-a759-95734a64b000)**: OK - **Me**: Let me permalink to the selection. - **[ChatGPT](https://chatgpt.com/share/6a389d6e-4180-83e8-a759-95734a64b000)**: OK - **Me**: Split this into a HTML and JSON file. - **[ChatGPT](https://chatgpt.com/share/6a389d6e-4180-83e8-a759-95734a64b000)**: OK ... and [here is the data visualization](https://sanand0.github.io/datastories/imf-gdp-forecast-errors/).