Made on
Sep 19, 2026
Price at call
$30.19
6-month call
Neutral -1.3%
Target by Mar 2027
$29.80
Great value below
$20.00
Model
v0.6.0
Projection vs Actual (6M history + forecast)
Forecast Change
-1.3% to $29.80
Predicted High
$30.50
at 5 months
Predicted Low
$25.80
at 2 months
Max Drawdown (predicted)
-14.5%
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 Sep 19, 2026 1:04 pm
Neutral
AMSC trends range-bound to
$29.80
(-1.3% from $30.19)
by Mar 2027.
dip-then-recover
ThesisAMSC sits between a bullish composite fair value near $41 and a bearish sentiment/regime backdrop with beta over 3, so the near-term path likely fades on risk-off pressure before value gravity partially reasserts. No earnings catalyst inside the window means drift and macro beta dominate. Endpoint lands modestly below current, close to the deterministic baseline but with a visible dip-and-recover shape.
Invalidated ifA sustained close above $36 on volume, or a breakdown below $22, would falsify this mean-reverting path.
| Checkpointtime after the call | Datewhen it gets graded | Predictedthe claim: closing price | Current priceactual close — fills in over time | Predicted returnpredicted vs $30.19 at call | Conv.brain's confidence, 1–10 | Driverwhy the brain put the point here |
|---|---|---|---|---|---|---|
| Prediction made | Sep 19, 2026 | — | $30.19 at call | — | — | The anchor — every point below is measured from this price and date. |
| 2 weeks | Oct 3, 2026 | $26.41–$33.97 typical range · internal point $29.10 | — | ±12.5% | 6/10 | Risk-off tape pressures high-beta turnaround immediately |
| What actually happened: closed $30.01 on Oct 2, 2026 = -0.6% vs the call (predicted -3.6%) · direction HIT (called flat, was flat) · off by 3.0 pp · accuracy 9/10 · typical range ±12.5%: inside the band · S&P +0.9% over the same window — lagged it | ||||||
| 1 month | Oct 19, 2026 | $24.71–$35.67 typical range · internal point $27.40 | — | ±18.1% | 5/10 | Sentiment overhang and no catalyst drag continues |
| 2 months | Nov 19, 2026 | $25.80 | — | -14.5% | 4/10 | Beta amplifies neutral regime chop into November |
| 3 months | Dec 19, 2026 | $27.20 | — | -9.9% | 4/10 | Value buyers emerge near bear scenario zone |
| 4 months | Jan 19, 2027 | $29.00 | — | -3.9% | 4/10 | January rebalancing and earnings anticipation lift |
| 5 months | Feb 19, 2027 | $30.50 | — | +1.0% | 4/10 | Q4 print potential draws fair-value gravity higher |
| 6 months | Mar 19, 2027 | $29.80 | — | -1.3% | 3/10 | Settles near baseline as macro uncertainty persists |
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 $29.22 (-3.2%) — 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 | $30.19 |
| Composite fair value | $41.19 |
| Signal-adjusted fair value | $43.59 |
| DCF fair value | $5.51 |
| Anchored-PE fair value | $150.13 |
| Buy-below (value lens) | $20.00 |
| Value net score | -57 |
| Value confidence | 6 / 10 |
| Quality net score | +30 |
| 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 49.0% 3m 62.9% 6m 74.2% |
| Daily σ (realism noise) | 4.0% |
| Beta vs S&P 500 | 1m 2.84 3m 3.52 5m 4.04 |
| Trailing 6-month return | -1.6% |
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 |
Sep 6, 2026 | 11d behind | AMSC-20260802-134056-8889 |
ext-forensic-memo |
Sep 17, 2026 | freshest | ext-AMSC-20260917-172318-652c |
ext-lens-quality |
Sep 17, 2026 | freshest | ext-AMSC-20260917-172318-652c |
ext-lens-sentiment |
Sep 17, 2026 | freshest | ext-AMSC-20260917-172318-652c |
ext-lens-value |
Sep 17, 2026 | freshest | ext-AMSC-20260917-172318-652c |
scenario-valuation |
Sep 17, 2026 | freshest | AMSC-20260802-134056-8889 |
valuation-synthesis |
Sep 17, 2026 | freshest | AMSC-20260802-134056-8889 |
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 | |
|---|---|---|---|---|---|---|---|
| Sep 19, 2026 | v0.6.0 | Neutral | $30.19 | $29.80 | -1.3% | Mar 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.