Forecast Alpha
Dashboard
Crypto RegDemo dataNO TRADE

[DEMO] Crypto regulatory bill passes Senate vote this week?

Market 55.0% against model 45.7%. Resolves in resolved, data updated 14d ago.

Share on X
Market
55.0%
Modelsim
45.7%
Edge EVsim
--
Confidencesim
0.78
Risksim
39
Liquidity
64
Volume
$102,400

Why this is not actionable

The model can still be informative here, but one or more gates blocks a trade call.

1 gate
Inside the 24h resolution-risk window — late-breaking information dominates any model edge.

Decision layer

No-trade decision

The model may still be informative, but at least one gate blocks an action-style signal.

NO TRADE
Edge
--
blocked

Expected value after costs, not raw probability spread.

Confidence
0.78
clear

How much support the model sees across available inputs.

Liquidity
64
clear

Thin markets can erase apparent edge through spread and slippage.

Risk
39
clear

Resolution ambiguity, timing, and data quality pressure the decision.

Data
75/100
clear

usable feature coverage.

Top blocking reasons
Inside the 24h resolution-risk window — late-breaking information dominates any model edge.

Why / why not trade

One decision layer for the market read.

This public box mirrors the internal diagnostic style without exposing execution controls: decision, probability gap, cost-adjusted edge, blocker, and next thing to monitor.

NO TRADE
Decision
No trade

no side selected

Model vs market
-9.3pt

45.7% model / 55.0% market

Edge after costs
--

fees, spread, slippage, risk

Top blocker
1 gate

Inside the 24h resolution-risk window — late-breaking information dominates any model edge.

Next watch condition

Inside the 24h resolution-risk window — late-breaking information dominates any model edge.

Read this market in three passes

1. Probability gap
-9.3pt

Model 45.7% vs market 55.0%.

2. Edge after costs
--

Raw disagreement is reduced by fees, spread, slippage, and risk controls.

3. Decision
NO TRADE

No trade

Why this read matters

The model may disagree with price, but the gates say the disagreement is not actionable right now.

Data quality
75/100
Open risksim
39
Liquidity
64
NO TRADE
Market
55.0%
Modelsim
45.7%
Edge (EV)sim
--
Confidencesim
0.78
Risk scoresim
39
Liquidity
64
Resolves in
resolved

Volume $102,400

Why the engine declines to trade this market

  • - Inside the 24h resolution-risk window — late-breaking information dominates any model edge.

Declining to trade is a feature: most markets are priced fairly within costs, and the risk gates run before any edge is considered.

Market-implied vs model probability

Market-impliedSOURCE: DEMOModel estimateSIMULATEDModel above marketModel below market

Factor attribution

SimulatedGen v3 - V3 feature-model

The model estimates a 9-point lower probability than the market, primarily driven by historical base rate and 7-day price momentum.

Factor attribution table showing how each input shifted the model probability
FACTORSIGNALWEIGHTLOG-ODDS ΔDIRECTIONDESCRIPTION
Historical base rate38%0.511BearishHistorical frequency for this kind of event — the prior before any market-specific evidence.
Cross-market divergence0.000.200.000NeutralLinked venue pricing the same event higher/lower (V2 scanner); 0 without an approved link.
7-day price momentum+0.360.35+0.125Bullish7-day drift of the market's own implied probability — sustained moves carry information.
BTC/ETH 7-day momentum+0.530.20+0.106Bullish7-day BTC/ETH return z-score, tanh-squashed.
Rate surprise0.252-year Treasury yield reaction in the 48 hours after the most recent scheduled release — a proxy for how markets interpreted the data versus expectations.
Yield curve shift0.1530-day change in the 10-year minus 2-year Treasury spread. A flattening curve signals tightening expectations; steepening signals easing.
News signal0.25Reliability-weighted direction of relevant news from the past 14 days. Official sources (filings, agency statements) carry more weight than commentary.
Crowd forecast0.20Calibration-weighted average of user probability estimates. Only applied when 5 or more weighted forecasters have submitted estimates.
Model probability43.0%Prior: 38% · Market: 55.0%
Confidence (λ)0.78Final: 45.7% = λ·model + (1−λ)·market
Confidence components: data quality 0.75 · factor agreement 0.89 · liquidity 0.64

Comparable eventshistorical base rate 37.5% - n=8

EventDateOutcomePrior mkt prob.
SEC vs Terraform/Do Kwon — Default judgment2024-04-05SEC won $4.5B judgment by default after Do Kwon convicted in Montenegro.--
SEC Crypto enforcement — Coinbase wins dismissal motion2024-03-27Court denied some SEC claims; case continues. Mixed for Coinbase.--
EU AI Act — Final passage2024-03-13EU AI Act passed European Parliament. First comprehensive AI law.92%
Binance — DOJ settlement and guilty plea2023-11-21Binance pled guilty, $4.3B fine. CZ resigned as CEO.60%
FTX — Sam Bankman-Fried criminal conviction2023-11-02CONVICTED on all 7 counts. Sentenced to 25 years.90%
SEC vs Ripple (XRP) — Summary judgment on programmatic sales2023-07-13Partial win for Ripple. Programmatic XRP sales not securities. Institutional sales were.35%
OpenAI — FTC investigation opened2023-07-13FTC opened investigation into OpenAI's data practices.--
EU MiCA Regulation — Final passage2023-04-20MiCA passed European Parliament. Comprehensive EU crypto framework.90%

Real historical events from the comparable-events library (showing 8 of 8 matched). The model's base rate is the realized frequency over the full matched set.

Scenario treeEngine template

Approved / enactedp=54% · EV(YES) +45¢Denied / rejectedp=46% · EV(YES) -55¢Decision issued before deadli…p=85%Delayed past deadlinep=15% · EV(YES) -55¢Ruling windowroot

Node probabilities are conditional on the parent; hover for cumulative path probability. Leaf EV is per $1 YES contract at the current price, before fees (fee-adjusted EVs in the table on the left).

PathPath prob.YES paysEV (YES, after costs)
Decision issued before deadline > Approved / enacted45.7%$1+41.6c
Decision issued before deadline > Denied / rejected39.4%$0-58.4c
Delayed past deadline14.9%$0-58.4c

Root-implied probability 45.7% reconciles with the model's 45.7% (±1pt invariant).

Why this mattersTemplate (no LLM key)

A 9.3% probability gap at a 55.0% price translates to 5.9% expected value per dollar of payout exposure after costs on the NO side. EV — not the raw probability gap — is the comparable number: the same gap is worth very different amounts at 50¢ and at 92¢.

What could make this wrongTemplate (no LLM key)

The model's edge depends on its inputs being right. Concretely: the base rate of 37.5% may not apply if this event differs structurally from its reference class; the pm.momentum_7d factor could be noise rather than information at this horizon; and with confidence at 0.78, the model itself concedes meaningful estimation error. The risk engine also flags: Inside the 24h resolution-risk window — late-breaking information dominates any model edge.

  • - Risk score 39/100 — composite of liquidity, volatility, time-to-resolution, data quality and category risk.
  • - Factor agreement 0.89: factors broadly agree, but shared blind spots are possible.
  • - Data quality 0.75 (simulated input in MVP).
  • - Simulated model values — this brief demonstrates structure, not live research.

Description

Resolution within 30 hours — inside the resolution-risk window.

Resolution criteria (verbatim, with analyzer flags)

ambiguity 8/100analyzed by heuristic

Resolves YES if the Senate passes the Digital Asset Market Clarity Act in the floor vote scheduled this week.

Resolves Mon, 15 Jun 2026 05:44:04 GMT. The contract pays on these exact criteria, not on the thesis.

Suggested paper position

The engine sizes NO TRADE markets to zero. Sizing never overrides the risk gates.

Paper position only. No real-money execution

Live open-market tracking

Market move
0.0pt
Toward model
Flat
Edge closed
-5.3pt
Snapshots
9

Since the first stored model read on 2026-06-09, the market has moved from 55.0% to 55.0%.

This is a directional diagnostic for unresolved markets, not final performance. Resolved outcomes still determine the official live record.

Data quality75/100 - usable

Demo seed — synthetic market datarel 90 - 1 feature
CoinGeckorel 90 - 1 feature
Forecast Alpha demo venuerel 90 - 3 features
Forecast Alpha scannerrel 90 - 1 feature
Comparable-events libraryrel 92 - 1 feature

Missing: News signal, Crowd forecast

When features are unavailable, the model increases uncertainty and weights the final estimate closer to the market price. Lower data quality does not mean the market is wrong. It means the model is being appropriately humble.

Risk factor breakdownsim

Inverse liquidity36
Price volatility18
Resolution proximity100
Data quality46
Category base risk65
Resolution ambiguity8
Regulatory exposure0
Portfolio concentration0

Composite score 39/100, higher = riskier.

Related markets

MarketMktDelta
Category context
BTC closes above $100k this week?
adjacent contract: nearby expiry + wording overlap
61.0%-2pt

Divergences > 5pt flagged in amber. For cross-venue pricing, see the Scanner.