Prediction Intelligence Platform

We tell you what AI
thinks will happen.

Four frontier AI models analyze prediction markets from Polymarket and Kalshi — both informed and blind. We track where AI consensus diverges from market odds and prove accuracy at 80.3% across 300 resolved markets.

Explore predictions View analytics API docs →

0.0%

Verified Accuracy

300Resolved

4AI Models

2Markets

80.3%ACCURACY

300RESOLVED

4AI MODELS

—BRIER

80.3%ACCURACY

300RESOLVED

4AI MODELS

—BRIER

Performance

Accuracy by domain

Every forecast resolved against verified outcomes. Brier scored and calibrated.

Full analytics dashboard

Platform

Three layers of prediction intelligence

01

Predictions

AI vs Markets

GPT-4o, Claude, Gemini, and Grok independently analyze prediction market odds. Informed and blind modes — toggle between market-aware and zero-knowledge predictions.

Updated 6x daily

02

Analytics

Forecasting Metrics

Brier scores, calibration curves, confidence signals, and category alpha — the full statistical profile of AI forecasting performance.

300+ resolved

03

Leaderboard

Model Performance

Which AI model is the most accurate forecaster? GPT-4o, Claude, Gemini, and Grok tracked head-to-head across 8 domains.

300+ resolved

Data Structure

Forecast taxonomy

Every forecast is classified into structured metadata — enabling filtering by domain, time horizon, specificity, and measurability for quantitative research.

{
  "domain":      "btc_price",
  "time_horizon": "months",
  "specificity":  4,
  "measurability": 5,
  "entities":     ["SEC", "BlackRock"],
  "keywords":     ["bitcoin", "etf"],
  "deadline":     "2026-06-01"
}

domainbtc_price, fed_rates, us_election

Specific forecast sub-domain

time_horizondays / weeks / months / quarters / years

Expected resolution timeframe

specificity1-5 scale

How precise the forecast is

measurability1-5 scale

Binary verifiable vs subjective

entitiesSEC, BlackRock, Fed

Companies, people, orgs referenced

resolution_deadline2026-06-01

Expected outcome date

Built for

Teams that need prediction data, not prediction markets

Hedge Funds & Asset Managers

Alternative data layer for systematic strategies. API-delivered AI forecast signals with verified Brier scores and accuracy track record.

Structured JSON/CSVBrier scoredDivergence signals

Quantitative Research

Machine-readable prediction data with calibration metrics across categories. Designed for data pipelines and backtesting.

5,000 API calls/dayCalibration curvesModel-level accuracy

Intelligence & Advisory

Track where AI models agree and disagree with market consensus. Blind and informed modes across geopolitics, finance, and tech.

4 AI modelsCross-domain coverageBlind predictions

Corporate Strategy

Monitor AI-market divergences across sectors. Prediction intelligence as an input to strategic planning and risk management.

Polymarket + KalshiCategory alphaReal-time updates

API

Data delivery for systematic teams

Predictions, analytics, and divergence signals — delivered as JSON or CSV via authenticated REST endpoints.

REST APIJSON + CSVAPI Key Auth5K req/dayBrier Scores

Developer docs

$ curl -H "X-API-Key: crn_..." \
  api-get.crene.com/api/predictions/analytics/

{
  "total_resolved": 736,
  "brier_scores":  {
    "ai_consensus": 0.5429,
    "market":       0.4144
  },
  "calibration":   [...],
  "category_alpha": {...}
}

Intelligence the market
hasn't priced in.

Explore AI predictions, or contact us for institutional API access.

Explore predictions Analytics dashboard

We tell you what AIthinks will happen.