S&P 500 7,489.72 +0.70% NASDAQ 25,373.85 +1.00% DOW 52,485.03 +0.50% RUT 2,604.40 -0.34% BTC-USD 63,514.00 +0.80% ETH-USD 3,412.60 -0.65% 10-YR 4.12 -0.72% 2-YR 3.86 +0.52% VIX 14.92 -2.67% GOLD 3,288.40 +0.43% WTI 71.86 -1.26% NATGAS 3.14 +1.95% NVDA 188.34 +1.90% MSFT 512.60 -0.28% AAPL 231.09 +0.46% AMZN 228.77 +1.16% GOOGL 196.42 -0.45% META 704.15 +1.41% TSLA 297.50 -2.11% AMD 172.88 +2.38%
JMM JMM RESEARCH FORECASTS, SCORED IN PUBLIC. See the track record

Method

Every number on this site can be traced to a public source, a frozen timestamp, and a score. This page is the contract.

Forecasting

Every probability is a member count over a simulated distribution, never an opinion. Weather calls use the ECMWF 50-member open-data ensemble, calibrated per settlement station against past observations. Price and event calls use Monte Carlo paths calibrated to options-implied volatility and base rates, with no alpha assumption. In both lanes the model trains only on data available before the forecast date, and forecasts freeze at publication; nothing is revised after the fact.

Scoring

Settled forecasts are graded with Brier and log scores against the executable market quote at forecast time, fees included. Both scores are published, including the ones we lose. A gap in contemporaneous quotes is marked as a gap, not filled in later.

Data sources and licenses

  • ECMWF open data — CC BY 4.0, attribution kept on every derived page.
  • NWS/NOAA forecasts and station observations — US public domain.
  • Venue market data — internal research use; displayed only with written permission.

Built on public data and infrastructure from

  • ECMWF
  • National Weather Service
  • Kalshi
  • Polymarket
  • GitHub
  • Cloudflare

Sources supply data; none endorse this site. Licenses and exact usage on the method page.

Editorial standards and corrections

Forecasts freeze at publication and are never edited after settlement. Articles state their sources with access dates. When we get something wrong, the correction is appended to the page, dated, with the original text preserved, and the page is listed on this site's corrections log. Claim checks quote the strongest version of the claim being tested, name where it circulated, and publish the query or dataset used to test it. We hold no positions in any market we forecast; the P&L on this site is a paper record.

Who runs this

JMM Research is a JMM Research publication. The pipeline that produces every number on this site runs on public infrastructure twice a day; its health is shown in the footer of every page. Contact: research@jmmresearch.com.

References

  • Brier, G. W. (1950). Verification of forecasts expressed in terms of probability. Monthly Weather Review, 78(1).
  • Gneiting, T., & Raftery, A. E. (2007). Strictly proper scoring rules, prediction, and estimation. JASA, 102(477).
  • ECMWF (2026). Ensemble forecasts: open data documentation.