WeatherEdgeby Prilo
PlansAPIBlogsDisclosureJoin our Discord
Back to WeatherEdge
Track record

How accurate is the model?

Every prediction is graded against the number that actually settles the market — the official NWS Climate Report (CLI) daily high. Not a blend of public models, not our own confidence. Here is the measured record over the last 120 days across 9 markets.

At dawn (the call you can trade)

The morning call, when Kalshi brackets are widest and the edge is largest. We don't claim to out-forecast the National Weather Service here — on settled days our morning error matches the NWS daily high almost exactly. What we add is a calibrated probability across the brackets, and then the convergence above as the day fills in.

1.60°F
model average miss, morning
1.65°F
NWS forecast miss, same days
70%
model within ±2°F, morning
706
settled mornings measured

Why this window matters: at the midday read the book is still undecided — its favorite bracket averages 61¢ and settles right 59% of the time (579 days). A view is worth having while the price still moves.

Did we call the winning bracket — and at what price?

Degrees are only half the story: what pays is naming the bracket that settles. Below is how often the bracket we named contained the official high, split by when we named it — and what that bracket cost at the time. A bracket caught late, at 90¢, is worth much less than the same bracket caught at dawn.

31%
called it in the morning
47¢
avg price of those morning calls
64%
morning missed, caught later
91¢
avg price of those later catches

The remaining 6% we never called correctly — counted here rather than quietly dropped. Measured over 36 settled days.

By midday

The same day re-read at noon, once the morning observations have landed but the afternoon peak is still ahead. Sharper than dawn — but the book has started to move too, so treat it as a revision, not a fresh edge.

47%
of settled days within ±1°F
1.42°F
average miss vs the official high
78%
within ±2°F
672
settled days measured
By market
MarketMorning missMidday missWithin ±1°F (midday)Market favorite (midday)Days
HoustonKHOU1.28°F1.25°F54%61¢84
MiamiKMIA1.20°F1.21°F56%63¢84
ChicagoKMDW1.58°F1.29°F52%59¢84
Los AngelesKLAX1.79°F1.16°F59%75¢83
New YorkKNYC1.79°F1.50°F33%64¢83
AtlantaKATL1.49°F1.40°F49%50¢83
San FranciscoKSFO2.25°F2.16°F27%53¢79
DallasKDFW1.42°F1.24°F46%61¢46
AustinKAUS1.53°F1.63°F46%62¢46

Method: each settled day compares the model's logged prediction to the official NWS CLI high for that station. Morning rows use the ~8 AM call with a live forecast anchor; midday rows use the station-local noon read and exclude days the observation feed was down (the μ would be computed blind). Backfilled and untrainable rows are excluded — the same gate the model's own learning uses. “Market favorite” is the average price of the Kalshi book's own top bracket at that same read, from our logged snapshot of the book — the honest measure of how much of the answer was already public when we published ours. We deliberately do notpublish a pre-close (5 PM) number: that read lands after the day's peak, when the market has already repriced, so scoring ourselves on it would flatter the model on exactly the days an earlier call had already cost someone money. Catch prices are the ask on the bracket we named at the moment we named it; where we never recorded a price we show “—” rather than substituting another number. Updated hourly.

Start your 7-day free trial →

See the live model against the market on your own dashboard.