AI Market Intelligence

Model forecasts, verified evidence, and runtime context translated into structured market briefs.

⌁

Market Pulse

Primary Focus
ETHUSDT
Bias
SHORT
Model Agreement
100%
High
Expected Move (H=1)
-1.94%
Evidence Quality
Medium
Reason: direction accuracy 49.9%
Runtime Status
Open exposure
Public runtime

Market at a Glance

2 market tickers synced
Ξ

ETHUSDT — AI Market Brief

Timeframe: H=1 (1 Day)Last Update: Jul 2, 2026

A. Current Model View

Direction / BiasSHORT
Expected Move-1.94%
Forecast Close$1,578.29
Reference Close$1,609.58
IssuedJul 1, 2026
TargetJul 2, 2026
Model Agreement100%
Active ModelOrion-II · Fusion-3A · Fusion-3N · Astra-II (in Fusion-3N)
Forecast vs Reference
1,6101,5991,5891,578recenttarget

B. Historical Reliability (ETHUSDT H=1)

Verified Forecast Rows3,240
Verified Days180
Models in Pool18
Avg Error (MAPE)2.67%
Median Error1.85%
Direction Accuracy49.85%
Touch Rate (Hit)72.56%
Recent MAPE1.89%
Days with Avg Error <1%12.5%
Forecast Rows <1% Error27.1%
Summary: Evidence 180d. Charts: overview recent rows (144 rows). Daily sub-1% uses average day error; row sub-1% uses individual forecast rows.
Direction Accuracy Trend
100%55%10%06-24: 22.2%06-25: 50.0%06-26: 38.9%06-27: 77.8%06-28: 94.4%06-29: 16.7%06-30: 83.3%07-01: 22.2%recent verified days
Hover points to see direction accuracy %.
Error Distribution
27.1%
<1%
19.4%
1–2%
25.0%
2–3%
23.6%
3–5%
4.9%
>5%

C. Scenario Map

+

Base Scenario (60%)

Models keep a SHORT bias while price behavior remains consistent with the reference area near $1,609.58. Target context: $1,578.29.

+

Downside Extension (25%)

A stronger downside extension is supported only if agreement stays firm and recent error does not expand materially.

!

Upside Invalidation Risk (15%)

The scenario weakens if price rejects the forecast path, volatility expands sharply, or evidence quality deteriorates against the upside path.

D. Risk Context

⚡Volatility RiskNormal
▣News / Event RiskMedium
⇄Spread RiskMedium
⌁Model AgreementHigh
↯Historical Acc. (Dir.)Moderate
〽Recent Model TrendImproving
Overall Risk: MEDIUM

E. Analyst Note

ETHUSDT shows a SHORT model bias for the next daily target, with expected move -1.94% and model agreement is 100%. Historical evidence quality is medium, so the useful value is in combining current direction with verified error history, volatility context, and runtime filters.

This is research context, not a trade signal.

What Changed Since Last Update

↑
Bias Change
SHORT → SHORT
↑
Expected Move
-2.42% → -1.94%
↑
Model Agreement
current 100%
=
Recent MAPE
4.70% → 1.89%
=
Runtime Status
Open exposure → Open exposure

Model Reliability Snapshot (ETHUSDT H+1)

ModelDirection Acc.Avg ErrorRecent MAPETouch RateTrend
Fusion-3A55.56%1.97%1.46%85.56%
Orion-II · standalone52.22%1.94%1.63%91.11%
Vega-II · in Fusion-3A54.44%1.99%1.55%72.22%
Nova-II · in Fusion-455.56%2.04%1.36%71.11%
Fusion-3B52.22%2.07%1.54%77.78%
View full evidence →

Weekly AI Research Brief

Computed from public Evidence summary and 90d model leaderboard. It does not mean an asset is a trading signal.
ⓘ
Lowest Avg Error
BTCUSDT · 2.05% MAPE
✕
Highest Avg Error
ETHUSDT · 2.67% MAPE
◎
Best Direction Accuracy
ETHUSDT · 49.85% direction
⇅
Weakest Direction Accuracy
BTCUSDT · 47.56% direction
≋
Most Stable Model
Orion-II · BTCUSDT · 1.51% MAPE
⌁
Where Runtime Filtered Out
BTCUSDT
⌬
Where Models Disagreed
No major disagreement in public forecast pool
◈
Strongest Agreement
BTCUSDT · 100%
▣
Evidence Note
Lowest MAPE is not the same as strongest trading signal; direction accuracy, touch rate, runtime state, and risk must be read separately.
View full weekly report →
What ProsQuant is not
Research output, not an investment instruction.
Not financial adviceNot a black-box signal sellerNot a profit guaranteeNot a broker or execution venue
Research only. Not financial advice. Not investment advice. Past performance is not indicative of future results.