Made on
Aug 18, 2026
Price at call
$97.81
6-month call
Bull +13.0%
Target by Feb 2027
$110.50
Great value below
$88.00
Model
v0.6.0
Projection vs Actual (6M history + forecast)
Forecast Change
+13.0% to $110.50
Predicted High
$110.50
at 6 months
Predicted Low
$98.20
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 18, 2026 3:09 am
Bull
ACGL trends higher to
$110.50
(+13.0% from $97.81)
by Feb 2027.
flat-then-break
ThesisACGL screens deeply undervalued on composite fair value and DCF, but the market has ignored this low-beta specialty insurer for months with no near-term catalyst. Expect modest drift with slight upward bias as value gravity slowly asserts, but nowhere near the deterministic baseline's $184 in six months absent a catalyst.
Invalidated ifBreak below $88 support or failure to reclaim $100 within two months signals value trap dynamics dominating.
| Checkpointtime after the call | Datewhen it gets graded | Predictedthe claim: closing price | Current priceactual close — fills in over time | Predicted returnpredicted vs $97.81 at call | Conv.brain's confidence, 1–10 | Driverwhy the brain put the point here |
|---|---|---|---|---|---|---|
| Prediction made | Aug 18, 2026 | — | $97.81 at call | — | — | The anchor — every point below is measured from this price and date. |
| 2 weeks | Sep 1, 2026 | $93.07–$102.55 typical range · internal point $98.20 | — | ±4.8% | 7/10 | Low-vol drift, no catalyst, risk-on tape ignores |
| What actually happened: closed $98.61 on Sep 1, 2026 = +0.8% vs the call (predicted +0.4%) · direction HIT (called flat, was flat) · off by 0.4 pp · accuracy 10/10 · typical range ±4.8%: inside the band · S&P -0.8% over the same window — beat it | ||||||
| 1 month | Sep 18, 2026 | $90.94–$104.68 typical range · internal point $99.10 | — | ±7.0% | 6/10 | Slow mean reversion off oversold sentiment |
| What actually happened: closed $96.70 on Sep 17, 2026 = -1.1% vs the call (predicted +1.3%) · direction HIT (called flat, was flat) · off by 2.5 pp · accuracy 9/10 · typical range ±7.0%: inside the band · S&P -0.7% over the same window — lagged it | ||||||
| 2 months | Oct 18, 2026 | $101.50 | — | +3.8% | 5/10 | Q3 earnings likely beats streak continues |
| 3 months | Nov 18, 2026 | $103.80 | — | +6.1% | 5/10 | Post-earnings modest rerating on book value |
| 4 months | Dec 18, 2026 | $105.50 | — | +7.9% | 4/10 | Year-end value rotation into cheap insurers |
| 5 months | Jan 18, 2027 | $108.00 | — | +10.4% | 4/10 | Valuation gap slowly narrows, analyst refresh |
| 6 months | Feb 18, 2027 | $110.50 | — | +13.0% | 3/10 | Value gravity partially closes discount over time |
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 $183.92 (+88.0%) — 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 | $97.81 |
| Composite fair value | $269.98 |
| Signal-adjusted fair value | $268.57 |
| DCF fair value | $326.56 |
| Anchored-PE fair value | $156.83 |
| Buy-below (value lens) | $88.00 |
| Value net score | -10 |
| Value confidence | 6 / 10 |
| Quality net score | +70 |
| 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 23.2% 3m 24.3% 6m 21.7% |
| Daily σ (realism noise) | 1.5% |
| Beta vs S&P 500 | 1m -0.50 3m -0.67 5m -0.25 |
| Trailing 6-month return | 0.8% |
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 |
Jul 30, 2026 | 17d behind | ACGL-20260730-203044-ef69 |
ext-forensic-memo |
Aug 17, 2026 | freshest | ext-ACGL-20260817-101753-0417 |
ext-lens-quality |
Aug 17, 2026 | freshest | ext-ACGL-20260817-101753-0417 |
ext-lens-sentiment |
Aug 17, 2026 | freshest | ext-ACGL-20260817-101753-0417 |
ext-lens-value |
Aug 17, 2026 | freshest | ext-ACGL-20260817-101753-0417 |
scenario-valuation |
Aug 17, 2026 | freshest | ACGL-20260730-215444-59f1 |
valuation-synthesis |
Aug 17, 2026 | freshest | ACGL-20260730-215444-59f1 |
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 18, 2026 | v0.6.0 | Bull | $97.81 | $110.50 | +13.0% | Feb 2027 | viewing |
| Jul 31, 2026 | v0.6.0 | Bull | $101.14 | $112.00 | +10.7% | Jan 2027 | 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.