Made on
Aug 3, 2026
Price at call
$336.25
6-month call
Bull +10.0%
Target by Feb 2027
$370.00
Great value below
$300.00
Model
v0.6.0
Projection vs Actual (6M history + forecast)
Forecast Change
+10.0% to $370.00
Predicted High
$370.00
at 6 months
Predicted Low
$334.00
in 2 weeks
Max Drawdown (predicted)
-0.7%
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 3, 2026 12:40 am
Bull
AXP trends higher to
$370.00
(+10.0% from $336.25)
by Feb 2027.
dip-then-recover
ThesisAXP trades at a modest discount to composite fair value with steady quality and neutral sentiment; expect gradual mean-reversion higher over 6 months, tempered by lukewarm post-earnings tape and no near-term catalyst until Q3 print in October.
Invalidated ifBreak below $300 on macro/credit stress, or failure to reclaim $345 after October earnings would falsify the recovery path.
| Checkpointtime after the call | Datewhen it gets graded | Predictedthe claim: closing price | Current priceactual close — fills in over time | Predicted returnpredicted vs $336.25 at call | Conv.brain's confidence, 1–10 | Driverwhy the brain put the point here |
|---|---|---|---|---|---|---|
| Prediction made | Aug 3, 2026 | — | $336.25 at call | — | — | The anchor — every point below is measured from this price and date. |
| 2 weeks | Aug 17, 2026 | $319.44–$353.06 typical range · internal point $334.00 | — | ±5.0% | 6/10 | neutral regime, no catalyst, mild post-earnings drift |
| What actually happened: closed $342.48 on Aug 14, 2026 = +1.9% vs the call (predicted -0.7%) · direction HIT (called flat, was flat) · off by 2.5 pp · accuracy 9/10 · typical range ±5.0%: inside the band · S&P +2.4% over the same window — lagged it | ||||||
| 1 month | Sep 3, 2026 | $311.89–$360.61 typical range · internal point $338.50 | — | ±7.2% | 5/10 | stabilization as macro pressure balances Buffett-halo bid |
| What actually happened: closed $329.98 on Sep 2, 2026 = -1.9% vs the call (predicted +0.7%) · direction HIT (called flat, was flat) · off by 2.5 pp · accuracy 9/10 · typical range ±7.2%: inside the band · S&P +0.9% over the same window — beat it | ||||||
| 2 months | Oct 3, 2026 | $345.00 | — | +2.6% | 5/10 | Q3 earnings approaches, beat history supports positioning |
| What actually happened: closed $302.78 on Oct 2, 2026 = -10.0% vs the call (predicted +2.6%) · direction MISS (called flat, was down) · off by 12.6 pp · accuracy 4/10 · S&P +1.6% over the same window — lagged it | ||||||
| 3 months | Nov 3, 2026 | $352.00 | — | +4.7% | 4/10 | post-print reaction likely positive given 4-of-5 beat cadence |
| 4 months | Dec 3, 2026 | $358.00 | — | +6.5% | 4/10 | value gravity toward $380 signal-adjusted fair value |
| 5 months | Jan 3, 2027 | $365.00 | — | +8.6% | 4/10 | year-end quality bid, compounder narrative reasserts |
| 6 months | Feb 3, 2027 | $370.00 | — | +10.0% | 3/10 | convergence toward deterministic baseline endpoint |
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 $373.48 (+11.1%) — 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
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 | $336.25 |
| Composite fair value | $402.23 |
| Signal-adjusted fair value | $380.50 |
| DCF fair value | $367.34 |
| Anchored-PE fair value | $472.01 |
| Buy-below (value lens) | $300.00 |
| Value net score | +25 |
| Value confidence | 6 / 10 |
| Quality net score | +73 |
| 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 30.2% 3m 25.1% 6m 29.0% |
| Daily σ (realism noise) | 1.6% |
| Beta vs S&P 500 | 1m 1.21 3m 0.67 5m 0.80 |
| Trailing 6-month return | -6.2% |
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 | AXP-20260803-000636-408a |
ext-forensic-memo |
Aug 3, 2026 | freshest | ext-AXP-20260803-002617-1442 |
ext-lens-quality |
Aug 3, 2026 | freshest | ext-AXP-20260803-002617-1442 |
ext-lens-sentiment |
Aug 3, 2026 | freshest | ext-AXP-20260803-002617-1442 |
ext-lens-value |
Aug 3, 2026 | freshest | ext-AXP-20260803-002617-1442 |
scenario-valuation |
Aug 3, 2026 | freshest | AXP-20260803-000636-408a |
valuation-synthesis |
Aug 3, 2026 | freshest | AXP-20260803-000636-408a |
Inputs flagged 7d+ behind the freshest one may be stale relative to the rest of the analysis.
Saved History
4 frozen snapshots — the record we score once predictions mature.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.