Forecast Alpha
Dashboard
MacroDemo dataLONG YES

S&P 500 closes above 5800 at end of Q3 2026?

Market 54.0% against model 67.0%. Resolves in 96d 10h, data updated 13d ago.

Share on X
Market
54.0%
Modelsim
67.0%
Edge EVsim
+9.8%
Confidencesim
0.69
Risksim
42
Liquidity
70
Volume
$122,500

Decision layer

Actionable research signal

The model disagreement survives the current gates. This is still research context, not financial advice.

LONG YES
Edge
+9.8%
clear

Expected value after costs, not raw probability spread.

Confidence
0.69
clear

How much support the model sees across available inputs.

Liquidity
70
clear

Thin markets can erase apparent edge through spread and slippage.

Risk
42
watch

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

Data
68/100
watch

usable feature coverage.

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.

LONG YES
Decision
Long YES research signal

side YES

Model vs market
+13.0pt

67.0% model / 54.0% market

Edge after costs
+9.8%

fees, spread, slippage, risk

Top blocker
Clear

Model edge survives the current public research gates.

Next watch condition

Watch resolution risk, timing, and data quality before trusting the gap.

Read this market in three passes

1. Probability gap
+13.0pt

Model 67.0% vs market 54.0%.

2. Edge after costs
+9.8%

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

3. Decision
LONG YES

Model leans YES

Why this read matters

The model-market gap currently survives the decision gates, but it is still research context and must be judged against the public track record.

Data quality
68/100
Open risksim
42
Liquidity
70
LONG YES
Market
54.0%
Modelsim
67.0%
Edge (EV)sim
+9.8%
Confidencesim
0.69
Risk scoresim
42
Liquidity
70
Resolves in
96d 10h

Volume $122,500

Market-implied vs model probability

Market-impliedSOURCE: DEMOModel estimateSIMULATEDModel above marketModel below market

Factor attribution

SimulatedGen v3 - V3 feature-model

The model estimates a 13-point higher probability than the market, primarily driven by historical base rate.

Factor attribution table showing how each input shifted the model probability
FACTORSIGNALWEIGHTLOG-ODDS ΔDIRECTIONDESCRIPTION
Historical base rate55%+0.201BullishHistorical frequency for this kind of event — the prior before any market-specific evidence.
Model probability67.0%Prior: 55% · Market: 54.0%
Confidence (λ)0.69Final: 67.0% = λ·model + (1−λ)·market
Confidence components: data quality 0.68 · factor agreement 0.70 · liquidity 0.70

Comparable eventsseeded prior 55% - 0 matches (min 8 for historical)

No comparable events matched for this market.

Scenario treeEngine template

Threshold hit in first half o…p=30% · EV(YES) +46¢Threshold hit in second halfp=37% · EV(YES) +46¢Never reaches threshold in wi…p=33% · EV(YES) -54¢Milestone 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)
Threshold hit in first half of window30.1%$1+42.8c
Threshold hit in second half36.9%$1+42.8c
Never reaches threshold in window33.0%$0-57.3c

Root-implied probability 67.0% reconciles with the model's 67.0% (±1pt invariant).

Description

Broad US equity index level at September 30, 2026 close.

Resolution criteria (verbatim, with analyzer flags)

ambiguity 8/100analyzed by heuristic

Resolves YES if the S&P 500 index closes above 5800 on September 30, 2026.

Resolves Thu, 01 Oct 2026 03:48:52 GMT. The contract pays on these exact criteria, not on the thesis.

Suggested paper position

SideYES
Entry54c
Kelly fraction1.5%
Quarter-Kelly, capped0.0%
Category used$0 / $15,000
Size$0

Paper position only. No real-money execution

Live open-market tracking

Market move
0.0pt
Toward model
Flat
Edge closed
-4.0pt
Snapshots
7

Since the first stored model read on 2026-06-09, the market has moved from 54.0% to 54.0%.

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

Data quality68/100 - usable

Demo seed — synthetic market datarel 90 - 1 feature
Demo seed — synthetic momentumrel 90 - 1 feature

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 liquidity30
Price volatility29
Resolution proximity0
Data quality10
Category base risk50
Resolution ambiguity8
Regulatory exposure0
Portfolio concentration0

Composite score 42/100, higher = riskier.