Quantitative#030

Statistical Arbitrage Across Baskets

Group dozens of related markets into a basket (say, every 2027 gubernatorial race) and trade the basket against its expected aggregate outcome rather than betting on any single race. The edge: individually the markets are noisy, but in aggregate their combined probability should hit a stable number, so when the basket's total drifts away from your model you trade the whole group back toward it.

What you need to run it

Pipeline to pull and normalize many market prices at once
Aggregate model with variance across the basket
Portfolio-level PnL attribution

Where this applies

Markets on Polymarket where statistical arbitrage across baskets is the natural play:

Every 2027 US gubernatorial race (e.g., NJ and VA) as one basket
Every 2026-27 Premier League relegation market as one basket
Every daily 'Bitcoin up today?' market across a month as one basket

Capabilities this demands

Model / quantCustom code / APISignificant capital

At a glance

CategoryQuantitative

Requirements3

CapabilitiesModel / quant, Custom code / API, Significant capital

VenuePolymarket (CLOB, Polygon)

Build it

Related quantitative 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 (147 strategies) or the data resources directory.