Made on
Aug 3, 2026
Price at call
$84.49
6-month call
Bear -12.4%
Target by Feb 2027
$74.00
Great value below
$40.00
Model
v0.6.0
Projection vs Actual (6M history + forecast)
Forecast Change
-12.4% to $74.00
Predicted High
$84.90
in 2 weeks
Predicted Low
$74.00
at 6 months
Max Drawdown (predicted)
-12.4%
Forecast
The masterbrain trajectory — 7 dated checkpoints. Short rungs (2w, 1m) show the typical range as the primary claim; point calls run from 2 months out. Every claim still gets graded. Predicted Aug 3, 2026 12:35 am
Bear
BHP trends lower to
$74.00
(-12.4% from $84.49)
by Feb 2027.
ride-then-fade
ThesisBHP trades far above composite fair value near $26 with weak sentiment and a fragile commodity narrative, but 6-month momentum is positive and no near-term earnings catalyst forces a rerating. Expect a gradual drift lower as value gravity slowly asserts, with high beta amplifying any regime softening into year-end.
Invalidated ifA sustained break above $92 on strong iron ore or copper prices, or sentiment flipping positive, would falsify the fade thesis.
| Checkpointtime after the call | Datewhen it gets graded | Predictedthe claim: closing price | Current priceactual close — fills in over time | Predicted returnpredicted vs $84.49 at call | Conv.brain's confidence, 1–10 | Driverwhy the brain put the point here |
|---|---|---|---|---|---|---|
| Prediction made | Aug 3, 2026 | — | $84.49 at call | — | — | The anchor — every point below is measured from this price and date. |
| 2 weeks | Aug 17, 2026 | $77.63–$91.35 typical range · internal point $84.90 | — | ±8.1% | 6/10 | Momentum and neutral regime hold price near current |
| What actually happened: closed $86.78 on Aug 14, 2026 = +2.7% vs the call (predicted +0.5%) · direction HIT (called flat, was flat) · off by 2.2 pp · accuracy 9/10 · typical range ±8.1%: inside the band · S&P +2.4% over the same window — lagged it | ||||||
| 1 month | Sep 3, 2026 | $74.55–$94.43 typical range · internal point $83.20 | — | ±11.8% | 5/10 | Sentiment drag begins nudging price lower |
| 2 months | Oct 3, 2026 | $81.00 | — | -4.1% | 5/10 | Value gravity and weak narrative pull down |
| 3 months | Nov 3, 2026 | $78.50 | — | -7.1% | 5/10 | Commodity fatigue and high beta amplify softness |
| 4 months | Dec 3, 2026 | $76.80 | — | -9.1% | 4/10 | Year-end positioning weighs on late-cycle names |
| 5 months | Jan 3, 2027 | $75.50 | — | -10.6% | 4/10 | Convergence toward deterministic baseline continues |
| 6 months | Feb 3, 2027 | $74.00 | — | -12.4% | 4/10 | Endpoint aligns with baseline fade to 74 |
Why ranges on the short rungs?
A 102-prediction trial (2026-07-21) showed 2-week point calls carry no information here —
three prompt formulations all lost to simply predicting zero — while the stock's own
volatility scale (σ×√t) described those windows well. So the short rungs claim what's
actually knowable: the typical travel, with earnings timing flagged where the variance
will come from. The internal point calls keep being generated and graded to map where
real skill begins. Full evidence: stocks/predictions/V0.5-DESIGN.md §8.
Deterministic control (v0.3 value line) targets $74.48 (-11.8%) — both lines get graded at every checkpoint, so the brain has to beat the formula, not just replace it. Brain: claude-opus-4-7.
Weaknesses
0 blocking · 1 degraded · 0 notes — follow the chain top-down (cause → effect).-
Degraded
[warning] Valuation is extremely fragile — almost no scenarios support the current price
Equation Inputs
Everything feeding the v0.6.0 model — value anchors, the stock's own price behaviour, and the tunable knobs.Value anchors (from deep analysis)
| Price at call | $84.49 |
| Composite fair value | $25.46 |
| Signal-adjusted fair value | $26.32 |
| DCF fair value | $25.78 |
| Anchored-PE fair value | $20.80 |
| Buy-below (value lens) | $40.00 |
| Value net score | -66 |
| Value confidence | 6 / 10 |
| Quality net score | +50 |
| Memo confidence | 7 / 10 |
| Deserved value (base) | — |
| Quality tilt | — |
| Deserved value (used) | — |
| Coherence (value × quality) | — |
Price behaviour (trailing — shapes the realism line)
| Realized volatility (annualized) | 1m 36.6% 3m 40.8% 6m 39.7% |
| Daily σ (realism noise) | 2.6% |
| Beta vs S&P 500 | 1m 1.74 3m 2.13 5m 2.04 |
| Trailing 6-month return | 17.1% |
Knobs (equation params)
| ladder | Array |
| llm_model | claude-opus-4-7 |
| max_tokens | 3000 |
| control_knobs | Array |
| Neutral band (%) | 5 |
| earnings_brief | v1 |
| prompt_version | p1 |
| control_version | v0.3.0 |
Version & Tech Chain
What produced this prediction — stamped on the record so versions can be compared by success rate later.
Model
v0.6.0
#271041f8fcd5 Tech composition (what this version is built from)
| # | Process | Kind | Group |
|---|---|---|---|
| 1 | Synthesis valuation-synthesis |
deterministic | final |
| 2 | Scenario Analysis scenario-valuation |
deterministic | valuation |
| 3 | Valuation / Mispricing ext-lens-value |
llm | extended |
| 4 | Company Quality ext-lens-quality |
llm | extended |
| 5 | Forensic Memo (combiner) ext-forensic-memo |
llm | extended |
| 6 | Classification company-classification |
llm | foundation |
| 7 | Live Quote fmp-quote |
data | market-data |
Inputs used (the runs that fed this prediction)
| Upstream process | Ran | Lag | Run id |
|---|---|---|---|
company-classification |
Aug 3, 2026 | freshest | BHP-20260803-000636-fd2d |
ext-forensic-memo |
Aug 3, 2026 | freshest | ext-BHP-20260803-002617-a296 |
ext-lens-quality |
Aug 3, 2026 | freshest | ext-BHP-20260803-002617-a296 |
ext-lens-sentiment |
Aug 3, 2026 | freshest | ext-BHP-20260803-002617-a296 |
ext-lens-value |
Aug 3, 2026 | freshest | ext-BHP-20260803-002617-a296 |
scenario-valuation |
Aug 3, 2026 | freshest | BHP-20260803-000636-fd2d |
valuation-synthesis |
Aug 3, 2026 | freshest | BHP-20260803-000636-fd2d |
Inputs flagged 7d+ behind the freshest one may be stale relative to the rest of the analysis.
Saved History
2 frozen snapshots — the record we score once predictions mature.| Made | Model | Call | At call | Target | Exp. | Eval due | |
|---|---|---|---|---|---|---|---|
| Aug 3, 2026 | v0.6.0 | Bear | $84.49 | $74.00 | -12.4% | Feb 2027 | viewing |
| Jun 30, 2026 | v0.3.0 | — | — | — | — | — | view |
Not Yet Modeled
What this v0.6.0 forecast deliberately ignores — the work ahead, in plain sight.- Scenario probabilities — one path, no bull/bear split (base_prob = 1.0).
- Intraday / sub-2-week behaviour — the first claim is at 14 days by design (EOD product).
- Position sizing / portfolio context — the path is a price claim only.