How it works
How Q forecasts, selects Signals, and learns from every resolved outcome.
Resolved markets
Every market Q forecast that has since resolved, with Q’s probability, the venue price it was scored against, and how the market settled.
Q turns any question into a calibrated probability.
- 01Classify the questionResolution rule, horizon, and question type.
- 02Map the landscapeActors, assets, linked markets, and related questions.
- 03Research the evidenceCheck the sources behind each claim.
- 04Build scenariosBase rates, pathways, dependencies, and disconfirming evidence.
- 05Produce the forecastA calibrated probability with uncertainty and cited analysis.
Signal selection
Q generates many forecasts. The best ones become Signals. Q curates markets where it sees a large spread and short-term catalysts that it believes will move the market in its direction.
- 500forecasts / day
- 100spread > 10pp
- 50meaningful liquidity
- 10resolve within a week
Q gets better over time.
Score each outcome
Compare Q and the forecast-time market price with the resolved result.
Diagnose the error
Trace the evidence, expert weights, and missing inputs behind the miss.
Feed the next model
Turn repeatable findings into fine-tuning and data changes.
Resolve · score · fine-tune · forecast again