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.

Some forecasts, like China, Singapore, UAE, Equatorial Guinea are consistently low.

Other forecasts, like Japan, Congo, Mexico, 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 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: 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: 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: On the IMF Data WEO site
  • Me: Check IMF GDP forecast accuracy.
  • ChatGPT: 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: For the current year, IMF typically underestimates. Next year onwards, they typically overestimate.
  • Me: Why? How?
  • ChatGPT: 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: OK
  • Me: Spread out the dots.
  • ChatGPT: OK
  • Me: Let me filter by country.
  • ChatGPT: OK
  • Me: Let me permalink to the selection.
  • ChatGPT: OK
  • Me: Split this into a HTML and JSON file.
  • ChatGPT: OK

… and here is the data visualization.