Weather Prediction Market Efficiency: 40,032-Contract Study

Published: April 2026 | Updated: July 2026 | OddsReference Research

Kalshi’s daily weather prediction markets are efficient. This paper analyzes 40,032 settled high-temperature contracts using an NWS MOS ensemble model that hits 33% bracket accuracy, twice the random baseline — but that genuine forecasting edge still cannot beat trading fees after execution costs.

Download the Full Paper (PDF)

What Does This Paper Find?

The core result: a genuinely skillful forecasting model still can’t beat the market. Three distinct trading strategies — tail-selling, conditional filtering, and a top-2 straddle — were tested against 40,032 settled contracts, and none cleared a reliable after-fee profit once realistic Kalshi trading costs were applied.

We analyze 40,032 settled daily high temperature contracts on the CFTC-regulated Kalshi prediction market exchange. Using an NWS MOS ensemble model combining GFS and NAM forecasts weighted by inverse RMSE, we achieve 33% bracket accuracy across 1,506 NYC events. Three trading strategies are tested: tail-selling (96.6% win rate, 0.62% ROI at taker fees), conditional filtering (45.2% on 93 events, likely overfit), and top-2 straddle (unprofitable at 76.5c market price vs 61.6c breakeven). Price convergence analysis on 804,248 hypothetical trades confirms smooth convergence: winners drift from 43.8c to 77c, losers from 15.2c to 4c. Markets incorporate NWS forecast updates within 10-30 minutes, but the 1-3c typical movement is smaller than round-trip trading costs of 3-3.5c. A mild favorite-longshot bias exists (0.4 pp on sub-10% contracts) but is too small to exploit. Underlying weather observations were cross-checked against NOAA’s official climate archive to confirm settlement actuals matched independent station records. We conclude that daily weather prediction markets on Kalshi are approximately efficient in the semi-strong sense.

What Are the Key Findings?

The table below summarizes the paper’s headline numbers: model accuracy, strategy returns, price convergence, and the efficiency verdict. Every figure comes from 40,032 settled Kalshi weather contracts and 804,248 trade-out scenarios — no tested strategy produced reliable profit once realistic trading costs were applied.

Why Doesn’t the Edge Survive Trading Fees?

Kalshi charges roughly 1.5-1.75 cents per side in taker fees — 3-3.5 cents round-trip. NWS forecast updates move weather contract prices only 1-3 cents. The cost of trading exceeds the available edge, which is exactly why every strategy tested in this paper failed to clear a reliable after-fee profit.

Run these round-trip costs against your own position size with the fee calculator, or find the exact price a contract needs to reach before a trade turns profitable with the break-even calculator. For a full platform-by-platform comparison of how Kalshi’s per-contract fee stacks up against Polymarket and other venues, see our prediction market fee guide.

How Is the Research Paper Structured?

The full PDF runs nine sections: introduction, market structure, data collection, model development, three trading-strategy tests, price convergence analysis, structural biases, discussion, and conclusion. Each section builds toward the same finding — public forecast data is priced in faster than any model can exploit it.

1. Introduction — Research questions and motivation
2. Market Structure — Contract design, fees, participant mix
3. Data — 48,978 weather observations, 46,248 CLI reports, 40,032 contracts
4. Model Development — NWS ensemble, uncertainty estimation, calibration
5. Trading Strategy Tests — Tail-selling, conditional filtering, top-2 straddle
6. Price Convergence Analysis — 804,248 trade scenarios, bracket rank effects, seasonal patterns
7. Structural Biases — Favorite-longshot bias, seasonal variation, volume patterns
8. Discussion — Efficiency interpretation, cross-domain comparison, market design implications
9. Conclusion — Summary and future directions

What Other Research Supports These Conclusions?

This paper is the academic companion to a two-paper efficiency series plus four detailed source articles. The companion crypto paper reaches the same semi-strong efficiency conclusion using a completely different asset class, which suggests the finding is structural to prediction markets rather than specific to weather.

• This paper: Weather market efficiency (NWS data, 40,032 contracts)
• Companion paper: Crypto market efficiency (877,606 contracts, three pricing models)

Source Articles

The underlying analysis is documented in four detailed articles:

• We Built a Weather Forecasting Model to Trade Kalshi — Model development and strategy testing
• 800,000 Trades Exposed: How Kalshi Weather Markets Converge — Convergence mechanics and microstructure
• Inside Kalshi’s Crypto Binary Options — Crypto market structure analysis
• We Backtested Three Pricing Models on 877,000 Crypto Contracts — Crypto pricing model backtest

For real-time prediction market data across all platforms, including live Kalshi weather contract pricing, visit our live dashboard.

Frequently Asked Questions

What is this weather prediction market research paper about?

This paper analyzes 40,032 settled Kalshi weather contracts using an NWS MOS ensemble model combining GFS and NAM forecasts weighted by inverse RMSE. We test three trading strategies across 1,506 NYC events and find that none produce positive after-fee returns, concluding that weather prediction markets are approximately efficient in the semi-strong sense.

Can you trade weather prediction markets profitably?

Our research found no profitable strategy using publicly available NWS data. Tail-selling achieved a 96.6% win rate but only 0.62% ROI at taker fees. Conditional filtering hit 45% on 93 events but every filter exceeding 40% had fewer than 120 qualifying events — the signature of overfitting. The market aggregates public forecast data within 10-30 minutes of release.

How accurate is the NWS ensemble model for weather trading?

The model achieves 33% top-1 bracket accuracy (2x random) and 61.6% top-2 accuracy using GFS and NAM forecasts weighted by inverse RMSE. While the model demonstrates genuine predictive skill, Kalshi markets already incorporate this same public data within 10-30 minutes of forecast release.

How does weather market efficiency compare to crypto markets?

Both domains show approximately efficient pricing. Weather markets exhibit a 0.4 pp favorite-longshot bias versus 2-4 pp in crypto markets. The smaller bias reflects lower emotional stakes — nobody has an identity-based attachment to a temperature bracket. Both markets incorporate public information within minutes and leave no exploitable edge after transaction costs.

Key Takeaways

• An NWS ensemble model achieves genuine predictive skill (33% bracket accuracy, 2x random) but cannot generate after-fee trading profits on Kalshi weather contracts
• Three strategies tested: tail-selling (marginally positive), conditional filtering (overfit), top-2 straddle (unprofitable at market prices)
• Kalshi’s 3-3.5 cent round-trip taker cost exceeds the typical 1-3 cent price move that follows an NWS update — use the fee calculator to check this math against your own trade size
• 804,248 trade scenarios confirm smooth price convergence with 10-30 minute NWS update incorporation
• Weather markets are approximately semi-strong efficient — the crowd aggregates public expert forecasts faster than any individual model
• Cross-domain comparison with crypto markets shows the same efficiency conclusion despite fundamentally different underlying assets