Economics & Macro · Quantitative#187

CPI Sub-Index Reconstruction

The headline inflation number is a weighted sum of components, and several of the heaviest ones — shelter, used cars, airfares, gasoline — can be estimated ahead of publication from private data that arrives much sooner. You rebuild the index bottom-up from those component estimates and compare your projection against the market's implied distribution before release day. The edge is that shelter alone is a third of the basket and follows rent data with a long, well-documented lag.

What you need to run it

  • Component-level private data (rent indices, used-car auction prices, retail fuel prices)
  • Correct BLS weighting scheme and seasonal-adjustment handling
  • Track record of your own forecast errors, so position size reflects real accuracy

Where this applies

Markets on Polymarket where cpi sub-index reconstruction is the natural play:

  • Will the next CPI print come in below 3.0%?
  • Will core CPI exceed 0.3% month-over-month in September 2026?
  • Will annual inflation be under 2.5% by December 2026?

Capabilities this demands

Data ingestionModel / quantDomain knowledge

At a glance

CategoryQuantitative
MarketEconomics & Macro
Requirements3
CapabilitiesData ingestion, Model / quant, Domain knowledge
VenuePolymarket (CLOB, Polygon)

Build it

Related economics & macro strategies

This is documentation, not advice. Poly Research & Robotics publishes how these strategies work because the method should be checkable — not as a recommendation to trade them. See the full strategy database (297 strategies) or the data resources directory.
Join Discord