Made on
Aug 11, 2026
Price at call
$104.72
6-month call
Bear -9.3%
Target by Feb 2027
$95.00
Great value below
$85.00
Model
v0.6.0
Projection vs Actual (6M history + forecast)
Forecast Change
-9.3% to $95.00
Predicted High
$106.80
at 1 month
Predicted Low
$95.00
at 6 months
Max Drawdown (predicted)
-9.3%
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 11, 2026 1:23 am
Bear
UPS trends lower to
$95.00
(-9.3% from $104.72)
by Feb 2027.
ride-then-fade
ThesisUPS is a wounded defensive compounder catching a modest sentiment bid from a risk-on tape and a fresh EPS beat, but composite fair value sits below current price and DCF anchors materially lower. Expect a brief drift higher on momentum, then value gravity reasserting toward the high-$90s to low-$90s over months.
Invalidated ifA close above $115 on positive guidance revisions, or a break below $88 signaling capitulation to DCF anchor, would invalidate this mean-reversion path.
| Checkpointtime after the call | Datewhen it gets graded | Predictedthe claim: closing price | Current priceactual close — fills in over time | Predicted returnpredicted vs $104.72 at call | Conv.brain's confidence, 1–10 | Driverwhy the brain put the point here |
|---|---|---|---|---|---|---|
| Prediction made | Aug 11, 2026 | — | $104.72 at call | — | — | The anchor — every point below is measured from this price and date. |
| 2 weeks | Aug 25, 2026 | $97.82–$111.62 typical range · internal point $106.10 | — | ±6.6% | 6/10 | Risk-on tape and post-beat drift extend near-term |
| 1 month | Sep 11, 2026 | $94.72–$114.72 typical range · internal point $106.80 | — | ±9.5% | 5/10 | Sentiment tailwind persists, no catalyst either way |
| 2 months | Oct 11, 2026 | $104.00 | — | -0.7% | 5/10 | Momentum fades as valuation concerns resurface |
| 3 months | Nov 11, 2026 | $100.50 | — | -4.0% | 5/10 | Q3 print approaches, value lens weighs |
| 4 months | Dec 11, 2026 | $98.00 | — | -6.4% | 5/10 | Drift toward composite fair value anchor |
| 5 months | Jan 11, 2027 | $96.50 | — | -7.8% | 4/10 | Value gravity dominates, quality drag persists |
| 6 months | Feb 11, 2027 | $95.00 | — | -9.3% | 4/10 | Settles near fair value, DCF pull unresolved |
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 $96.26 (-8.1%) — 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] Sector in contraction — demand weakening across the industry
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 | $104.72 |
| Composite fair value | $97.69 |
| Signal-adjusted fair value | $88.47 |
| DCF fair value | $71.64 |
| Anchored-PE fair value | $164.91 |
| Buy-below (value lens) | $85.00 |
| Value net score | -60 |
| Value confidence | 7 / 10 |
| Quality net score | -17 |
| 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 38.2% 3m 33.1% 6m 33.9% |
| Daily σ (realism noise) | 2.1% |
| Beta vs S&P 500 | 1m 0.82 3m 0.93 5m 1.02 |
| Trailing 6-month return | -10.8% |
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 11, 2026 | freshest | UPS-20260811-000713-2def |
ext-forensic-memo |
Aug 11, 2026 | freshest | ext-UPS-20260811-010850-84b7 |
ext-lens-quality |
Aug 11, 2026 | freshest | ext-UPS-20260811-010850-84b7 |
ext-lens-sentiment |
Aug 11, 2026 | freshest | ext-UPS-20260811-010850-84b7 |
ext-lens-value |
Aug 11, 2026 | freshest | ext-UPS-20260811-010850-84b7 |
scenario-valuation |
Aug 11, 2026 | freshest | UPS-20260811-000713-2def |
valuation-synthesis |
Aug 11, 2026 | freshest | UPS-20260811-000713-2def |
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 11, 2026 | v0.6.0 | Bear | $104.72 | $95.00 | -9.3% | Feb 2027 | viewing |
| Jul 12, 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.