Made on
Aug 5, 2026
Price at call
$77.10
6-month call
Bear -8.6%
Target by Feb 2027
$70.50
Great value below
$59.00
Model
v0.6.0
Projection vs Actual (6M history + forecast)
Forecast Change
-8.6% to $70.50
Predicted High
$78.50
at 1 month
Predicted Low
$70.50
at 6 months
Max Drawdown (predicted)
-8.6%
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 5, 2026 2:42 am
Bear
OLLI trends lower to
$70.50
(-8.6% from $77.10)
by Feb 2027.
ride-then-fade
ThesisOLLI screens rich versus fair value ($69) but a low-beta compounder narrative plus risk-on tape keeps the tape sticky near current levels; over 6 months value gravity slowly pulls price toward the high-$60s with a modest bounce attempt into a likely fall earnings print.
Invalidated ifA close above $85 on strong comps or below $65 on a guide-down would break this drift-lower thesis.
| Checkpointtime after the call | Datewhen it gets graded | Predictedthe claim: closing price | Current priceactual close — fills in over time | Predicted returnpredicted vs $77.10 at call | Conv.brain's confidence, 1–10 | Driverwhy the brain put the point here |
|---|---|---|---|---|---|---|
| Prediction made | Aug 5, 2026 | — | $77.10 at call | — | — | The anchor — every point below is measured from this price and date. |
| 2 weeks | Aug 19, 2026 | $69.33–$84.87 typical range · internal point $77.80 | — | ±10.1% | 6/10 | Risk-on tape and low-beta bid sustain price |
| What actually happened: closed $78.78 on Aug 19, 2026 = +2.2% vs the call (predicted +0.9%) · direction HIT (called flat, was flat) · off by 1.3 pp · accuracy 10/10 · typical range ±10.1%: inside the band · S&P +0.2% over the same window — beat it | ||||||
| 1 month | Sep 5, 2026 | $65.84–$88.36 typical range · internal point $78.50 | — | ±14.6% | 5/10 | Sentiment tailwind extends into early September |
| What actually happened: closed $76.57 on Sep 4, 2026 = -0.7% vs the call (predicted +1.8%) · direction HIT (called flat, was flat) · off by 2.5 pp · accuracy 9/10 · typical range ±14.6%: inside the band · S&P -0.1% over the same window — lagged it | ||||||
| 2 months | Oct 5, 2026 | $76.20 | — | -1.2% | 5/10 | Valuation gravity begins nudging price lower |
| What actually happened: closed $88.06 on Oct 2, 2026 = +14.2% vs the call (predicted -1.2%) · direction MISS (called flat, was up) · off by 15.4 pp · accuracy 4/10 · S&P 0.0% over the same window — lagged it | ||||||
| 3 months | Nov 5, 2026 | $74.00 | — | -4.0% | 4/10 | Q3 print pressures multiple toward fair value |
| 4 months | Dec 5, 2026 | $72.50 | — | -6.0% | 4/10 | Post-earnings drift, tax-loss selling adds weight |
| 5 months | Jan 5, 2027 | $71.00 | — | -7.9% | 3/10 | Convergence toward composite fair value $69 |
| 6 months | Feb 5, 2027 | $70.50 | — | -8.6% | 3/10 | Settles just above anchor as compounder base holds |
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 $77.47 (+0.5%) — 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
No weaknesses recorded for this run.All inputs present, no fallbacks used — nothing to flag.
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 | $77.10 |
| Composite fair value | $69.10 |
| Signal-adjusted fair value | $69.64 |
| DCF fair value | $68.01 |
| Anchored-PE fair value | $96.45 |
| Buy-below (value lens) | $59.00 |
| Value net score | -65 |
| Value confidence | 7 / 10 |
| Quality net score | +77 |
| 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 43.7% 3m 50.6% 6m 44.9% |
| Daily σ (realism noise) | 3.2% |
| Beta vs S&P 500 | 1m 0.72 3m 0.84 5m 0.71 |
| Trailing 6-month return | -29.9% |
Knobs (equation params)
| ladder | ["w2","m1","m2","m3","m4","m5","m6"] |
| llm_model | claude-opus-4-7 |
| max_tokens | 3000 |
| control_knobs | {"w_dcf":0.5,"k_qual":0.200000000000000011102230246251565404236316680908203125,"reach_6m":0.450000000000000011102230246251565404236316680908203125,"coh_floor":0.5,"conf_gain":0.059999999999999997779553950749686919152736663818359375,"noise_phi":0.84999999999999997779553950749686919152736663818359375,"conf_floor":0.40000000000000002220446049250313080847263336181640625,"w_composite":0.5,"noise_window":"3m","flat_band_pct":5,"horizon_months":6,"noise_sigma_fallback":0.01499999999999999944488848768742172978818416595458984375} |
| 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 | OLLI-20260803-120351-5ad0 |
ext-forensic-memo |
Aug 3, 2026 | freshest | ext-OLLI-20260803-133031-4540 |
ext-lens-quality |
Aug 3, 2026 | freshest | ext-OLLI-20260803-133031-4540 |
ext-lens-sentiment |
Aug 3, 2026 | freshest | ext-OLLI-20260803-133031-4540 |
ext-lens-value |
Aug 3, 2026 | freshest | ext-OLLI-20260803-133031-4540 |
scenario-valuation |
Aug 3, 2026 | freshest | OLLI-20260803-120351-5ad0 |
valuation-synthesis |
Aug 3, 2026 | freshest | OLLI-20260803-120351-5ad0 |
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 5, 2026 | v0.6.0 | Bear | $77.10 | $70.50 | -8.6% | 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.