Made on
Aug 28, 2026
Price at call
$72.18
6-month call
Bear -26.6%
Target by Feb 2027
$53.00
Great value below
$55.00
Model
v0.6.0
Projection vs Actual (6M history + forecast)
Forecast Change
-26.6% to $53.00
Predicted High
$71.20
in 2 weeks
Predicted Low
$53.00
at 6 months
Max Drawdown (predicted)
-26.6%
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 28, 2026 1:07 pm
Bear
ON trends lower to
$53.00
(-26.6% from $72.18)
by Feb 2027.
ride-then-fade
ThesisON trades far above every value anchor with a cracked sentiment backdrop and dilutive M&A overhang, so the path drifts lower as the risk-on tape's support fades and gravity toward the mid-$50s asserts itself. High beta amplifies chop but not direction; no earnings catalyst inside window means value gravity dominates months 2-6.
Invalidated ifA decisive break above $80 on volume or a credible narrative reset (M&A accretion clarity, SiC demand upgrade) would falsify the drift lower.
| Checkpointtime after the call | Datewhen it gets graded | Predictedthe claim: closing price | Current priceactual close — fills in over time | Predicted returnpredicted vs $72.18 at call | Conv.brain's confidence, 1–10 | Driverwhy the brain put the point here |
|---|---|---|---|---|---|---|
| Prediction made | Aug 28, 2026 | — | $72.18 at call | — | — | The anchor — every point below is measured from this price and date. |
| 2 weeks | Sep 11, 2026 | $59.85–$84.51 typical range · internal point $71.20 | — | ±17.1% | 6/10 | Risk-on tape and high beta keep price near spot |
| What actually happened: closed $70.17 on Sep 10, 2026 = -2.8% vs the call (predicted -1.4%) · direction HIT (called flat, was flat) · off by 1.4 pp · accuracy 10/10 · typical range ±17.1%: inside the band · S&P -1.6% over the same window — lagged it | ||||||
| 1 month | Sep 28, 2026 | $54.31–$90.05 typical range · internal point $69.00 | — | ±24.8% | 6/10 | Sentiment cracks reassert as regime ages |
| 2 months | Oct 28, 2026 | $65.50 | — | -9.3% | 5/10 | Value gravity begins pulling toward anchors |
| 3 months | Nov 28, 2026 | $62.00 | — | -14.1% | 5/10 | No catalyst; forensic and quality drag compound |
| 4 months | Dec 28, 2026 | $58.50 | — | -19.0% | 4/10 | Year-end derisking on high-beta EV/SiC names |
| 5 months | Jan 28, 2027 | $55.00 | — | -23.8% | 4/10 | Approaches value-lens attractive threshold |
| 6 months | Feb 28, 2027 | $53.00 | — | -26.6% | 3/10 | Converges near deterministic baseline endpoint |
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 $52.85 (-26.8%) — 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 · 2 notes — follow the chain top-down (cause → effect).-
Degraded
[critical] AI analysis identifies strong headwinds — multiple forces working against this stock
-
Note
EPV de-weighted — growth IS the value proposition for this type of company
-
Note
Valuation anchor absent: anchored_pe.
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 | $72.18 |
| Composite fair value | $18.22 |
| Signal-adjusted fair value | $15.53 |
| DCF fair value | $17.92 |
| Anchored-PE fair value | — |
| Buy-below (value lens) | $55.00 |
| Value net score | -72 |
| Value confidence | 6 / 10 |
| Quality net score | -7 |
| 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 44.3% 3m 85.8% 6m 76.1% |
| Daily σ (realism noise) | 5.4% |
| Beta vs S&P 500 | 1m 1.53 3m 3.24 5m 3.27 |
| Trailing 6-month return | 9.7% |
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 28, 2026 | freshest | ON-20260828-030001-9b48 |
ext-forensic-memo |
Aug 28, 2026 | freshest | ext-ON-20260828-032401-84fd |
ext-lens-quality |
Aug 28, 2026 | freshest | ext-ON-20260828-032401-84fd |
ext-lens-sentiment |
Aug 28, 2026 | freshest | ext-ON-20260828-032401-84fd |
ext-lens-value |
Aug 28, 2026 | freshest | ext-ON-20260828-032401-84fd |
scenario-valuation |
Aug 28, 2026 | freshest | ON-20260828-030001-9b48 |
valuation-synthesis |
Aug 28, 2026 | freshest | ON-20260828-030001-9b48 |
Inputs flagged 7d+ behind the freshest one may be stale relative to the rest of the analysis.
Saved History
1 frozen snapshot — the record we score once predictions mature.| Made | Model | Call | At call | Target | Exp. | Eval due | |
|---|---|---|---|---|---|---|---|
| Aug 28, 2026 | v0.6.0 | Bear | $72.18 | $53.00 | -26.6% | Feb 2027 | viewing |
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.