DEMO PREVIEW — Markets and probabilities shown are sample data, not real model output. Our ML engine is in development.

Get notified at launch →
Get notified at launch
← Back RESEARCH / POLITICS / POLYMARKET

Democrats retake the US House in the 2026 midterm

B CONFIDENCE

Sample market — design preview only. No real model output. The probabilities, edge, confidence grade, drivers and chart below are placeholder data while our ML engine is in development. Get notified at launch.

MARKET
58.0%
MODEL
64.0%
EDGE
+6.0pp
Sample data
VOL $5.2M · 14d range 51% – 65%
MODEL · IN DEVELOPMENT
·
Read the planned methodology
60-DAY PROBABILITY · MARKET vs MODEL
MARKET
MODEL
7D 30D 60D ALL
49% 54% 59% 64% 69%
WHAT'S DRIVING THIS
Top-weighted features in the current model fit. Direction shown vs. baseline market price; magnitude is shapley-normalized contribution.
Generic-ballot polling D+3.1 (60-day avg)
↑ 55%
Incumbent presidential approval (40d window)
↑ 48%
Recruitment gap in toss-up districts
↑ 32%
Redistricting effects in NY/NC
↓ 34%
Feature pipeline: ~140 inputs across rate-curve, options, macro prints, and platform-level liquidity. Refit nightly at 03:30 UTC.
HONEST READ
MODEL CONFIDENCE 90% CI: 58% – 70%
BRIER (POLITICS) 0.209
VS MARKET BASELINE -0.006
RESOLVED IN CATEGORY 142
We have measurable edge in politics over 142 resolved markets. Edge ≠ certainty — the 90% CI is wide because base rates here are noisy.
COMPARABLE HISTORICAL EVENTS
N = 3
Date Question Outcome Our model said
2018-11-06 Dems retake House 2018 midterm YES 78%
2022-11-08 Dems hold House 2022 midterm NO 31%
2010-11-02 GOP retakes House 2010 midterm YES 83%

Related markets

More in politics
NOT FINANCIAL ADVICE. MODELS CAN BE WRONG. RISK OF TOTAL LOSS.
We don't take positions. We don't route orders. Our calibration is published with every number on this page — read it before acting on anything you see here.