Made on
Jul 31, 2026
Price at call
$954.17
6-month call
Bear -6.2%
Target by Jan 2027
$895.00
Great value below
$700.00
Model
v0.6.0
Projection vs Actual (6M history + forecast)
Forecast Change
-6.2% to $895.00
Predicted High
$956.00
in 2 weeks
Predicted Low
$895.00
at 6 months
Max Drawdown (predicted)
-6.2%
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 Jul 31, 2026 12:49 am
Bear
COST trends lower to
$895.00
(-6.2% from $954.17)
by Jan 2027.
ride-then-fade
ThesisCOST is richly valued but the quality/sentiment shield and defensive low-beta profile keep it resilient in a neutral tape; expect modest drift lower as multiple compression edges in, but nowhere near fair value in 6 months.
Invalidated ifA break below $880 on heavy volume or a comp-sales miss would accelerate derating; sustained hold above $970 invalidates the fade.
| Checkpointtime after the call | Datewhen it gets graded | Predictedthe claim: closing price | Current priceactual close — fills in over time | Predicted returnpredicted vs $954.17 at call | Conv.brain's confidence, 1–10 | Driverwhy the brain put the point here |
|---|---|---|---|---|---|---|
| Prediction made | Jul 31, 2026 | — | $954.17 at call | — | — | The anchor — every point below is measured from this price and date. |
| 2 weeks | Aug 14, 2026 | $909.54–$998.80 typical range · internal point $956.00 | — | ±4.7% | 7/10 | Low-beta drift, no catalyst, quiet-quality bid intact |
| What actually happened: closed $961.85 on Aug 13, 2026 = +0.8% vs the call (predicted +0.2%) · direction HIT (called flat, was flat) · off by 0.6 pp · accuracy 10/10 · typical range ±4.7%: inside the band · S&P +4.1% over the same window — beat it | ||||||
| 1 month | Aug 31, 2026 | $889.49–$1,018.85 typical range · internal point $948.00 | — | ±6.8% | 6/10 | Mild summer fade as premium multiple weighs |
| 2 months | Oct 1, 2026 | $935.00 | — | -2.0% | 5/10 | Valuation gravity nudges lower into fall |
| 3 months | Oct 31, 2026 | $928.00 | — | -2.7% | 5/10 | Comp-sales print risk, defensive bid persists |
| 4 months | Dec 1, 2026 | $915.00 | — | -4.1% | 4/10 | Year-end multiple compression, tax-loss avoidance limits |
| 5 months | Dec 31, 2026 | $905.00 | — | -5.2% | 4/10 | Rich PE slowly derating in neutral regime |
| 6 months | Jan 31, 2027 | $895.00 | — | -6.2% | 3/10 | Continued slow drift toward anchored-PE fair value |
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 $832.96 (-12.7%) — 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
[caution] 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 | $954.17 |
| Composite fair value | $299.30 |
| Signal-adjusted fair value | $331.96 |
| DCF fair value | $282.31 |
| Anchored-PE fair value | $432.83 |
| Buy-below (value lens) | $700.00 |
| Value net score | -78 |
| Value confidence | 8 / 10 |
| Quality net score | +88 |
| Memo confidence | 8 / 10 |
| Deserved value (base) | — |
| Quality tilt | — |
| Deserved value (used) | — |
| Coherence (value × quality) | — |
Price behaviour (trailing — shapes the realism line)
| Realized volatility (annualized) | 1m 25.1% 3m 23.5% 6m 21.3% |
| Daily σ (realism noise) | 1.5% |
| Beta vs S&P 500 | 1m -0.89 3m -0.57 5m -0.29 |
| Trailing 6-month return | -0.7% |
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 |
Jul 31, 2026 | freshest | COST-20260731-001023-19e3 |
ext-forensic-memo |
Jul 31, 2026 | freshest | ext-COST-20260731-003545-e21e |
ext-lens-quality |
Jul 31, 2026 | freshest | ext-COST-20260731-003545-e21e |
ext-lens-sentiment |
Jul 31, 2026 | freshest | ext-COST-20260731-003545-e21e |
ext-lens-value |
Jul 31, 2026 | freshest | ext-COST-20260731-003545-e21e |
scenario-valuation |
Jul 31, 2026 | freshest | COST-20260731-001023-19e3 |
valuation-synthesis |
Jul 31, 2026 | freshest | COST-20260731-001023-19e3 |
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 | |
|---|---|---|---|---|---|---|---|
| Jul 31, 2026 | v0.6.0 | Bear | $954.17 | $895.00 | -6.2% | Jan 2027 | viewing |
| Jun 24, 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.