Made on
Aug 26, 2026
Price at call
$77.34
6-month call
Bull +7.6%
Target by Feb 2027
$83.20
Great value below
$68.00
Model
v0.6.0
Projection vs Actual (6M history + forecast)
Forecast Change
+7.6% to $83.20
Predicted High
$83.20
at 6 months
Predicted Low
$77.90
in 2 weeks
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 26, 2026 1:14 pm
Bull
SHG trends higher to
$83.20
(+7.6% from $77.34)
by Feb 2027.
flat-then-break
ThesisSHG trades below composite fair value ($83.69) with steady earnings beats but weak sentiment and no near-term catalyst. Expect a slow drift toward fair value over months, with early chop from a risk-on tape and beta ~1.08 providing modest lift.
Invalidated ifBreak below $72 on heavy volume or Korean bank sector shock invalidates upward drift
| Checkpointtime after the call | Datewhen it gets graded | Predictedthe claim: closing price | Current priceactual close — fills in over time | Predicted returnpredicted vs $77.34 at call | Conv.brain's confidence, 1–10 | Driverwhy the brain put the point here |
|---|---|---|---|---|---|---|
| Prediction made | Aug 26, 2026 | — | $77.34 at call | — | — | The anchor — every point below is measured from this price and date. |
| 2 weeks | Sep 9, 2026 | $71.07–$83.61 typical range · internal point $77.90 | — | ±8.1% | 6/10 | Risk-on regime provides mild tailwind near term |
| What actually happened: closed $83.54 on Sep 8, 2026 = +8.0% vs the call (predicted +0.7%) · direction MISS (called flat, was up) · off by 7.3 pp · accuracy 4/10 · typical range ±8.1%: inside the band · S&P 0.0% over the same window — beat it | ||||||
| 1 month | Sep 26, 2026 | $68.25–$86.43 typical range · internal point $78.60 | — | ±11.8% | 6/10 | Beta lift continues, no catalyst but stable tape |
| 2 months | Oct 26, 2026 | $79.80 | — | +3.2% | 5/10 | Slow grind toward fair value, sentiment neutral |
| 3 months | Nov 26, 2026 | $80.50 | — | +4.1% | 5/10 | Value gravity pulls toward baseline endpoint |
| 4 months | Dec 26, 2026 | $81.60 | — | +5.5% | 4/10 | Year-end positioning in Korean financials |
| 5 months | Jan 26, 2027 | $82.40 | — | +6.5% | 4/10 | Earnings season anticipation, prior beats support |
| 6 months | Feb 26, 2027 | $83.20 | — | +7.6% | 4/10 | Convergence toward composite fair value $83.69 |
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 $80.89 (+4.6%) — 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 · 1 note — follow the chain top-down (cause → effect).-
Degraded
[warning] Revenue is volatile and unreliable — growth projections are speculative
-
Note
Valuation anchor absent: dcf.
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 | $77.34 |
| Composite fair value | $83.69 |
| Signal-adjusted fair value | $83.77 |
| DCF fair value | — |
| Anchored-PE fair value | $46.67 |
| Buy-below (value lens) | $68.00 |
| Value net score | +16 |
| Value confidence | 6 / 10 |
| Quality net score | +24 |
| Memo confidence | 6 / 10 |
| Deserved value (base) | — |
| Quality tilt | — |
| Deserved value (used) | — |
| Coherence (value × quality) | — |
Price behaviour (trailing — shapes the realism line)
| Realized volatility (annualized) | 1m 36.1% 3m 40.7% 6m 36.5% |
| Daily σ (realism noise) | 2.6% |
| Beta vs S&P 500 | 1m 1.42 3m 1.08 5m 1.10 |
| Trailing 6-month return | 9.1% |
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 26, 2026 | freshest | SHG-20260826-023001-37fc |
ext-forensic-memo |
Aug 26, 2026 | freshest | ext-SHG-20260826-035541-7138 |
ext-lens-quality |
Aug 26, 2026 | freshest | ext-SHG-20260826-035541-7138 |
ext-lens-sentiment |
Aug 26, 2026 | freshest | ext-SHG-20260826-035541-7138 |
ext-lens-value |
Aug 26, 2026 | freshest | ext-SHG-20260826-035541-7138 |
valuation-synthesis |
Aug 26, 2026 | freshest | SHG-20260826-023001-37fc |
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 26, 2026 | v0.6.0 | Bull | $77.34 | $83.20 | +7.6% | 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.