Made on
Aug 5, 2026
Price at call
$66.79
6-month call
Neutral +3.3%
Target by Feb 2027
$69.00
Great value below
$52.00
Model
v0.6.0
Projection vs Actual (6M history + forecast)
Forecast Change
+3.3% to $69.00
Predicted High
$69.50
at 1 month
Predicted Low
$66.00
at 3 months
Max Drawdown (predicted)
-1.2%
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 2:39 am
Neutral
SWKS trends range-bound to
$69.00
(+3.3% from $66.79)
by Feb 2027.
ride-then-fade
ThesisSWKS trades near composite fair value with a mildly negative sentiment overlay but supportive risk-on regime and 5/5 earnings beat streak. Expect early drift higher on momentum and beta into risk-on tape, then gravity toward the $65-70 fair value band, with a late-window Q4 print potentially adding volatility.
Invalidated ifA close below $58 would break the value-support floor and invalidate the mean-reversion thesis; a break above $75 would signal a regime shift not captured here.
| Checkpointtime after the call | Datewhen it gets graded | Predictedthe claim: closing price | Current priceactual close — fills in over time | Predicted returnpredicted vs $66.79 at call | Conv.brain's confidence, 1–10 | Driverwhy the brain put the point here |
|---|---|---|---|---|---|---|
| Prediction made | Aug 5, 2026 | — | $66.79 at call | — | — | The anchor — every point below is measured from this price and date. |
| 2 weeks | Aug 19, 2026 | $58.23–$75.35 typical range · internal point $68.20 | — | ±12.8% | 6/10 | Risk-on regime and high beta lift near-term |
| What actually happened: closed $69.49 on Aug 19, 2026 = +4.0% vs the call (predicted +2.1%) · direction HIT (called flat, was flat) · off by 1.9 pp · accuracy 10/10 · typical range ±12.8%: inside the band · S&P +0.2% over the same window — beat it | ||||||
| 1 month | Sep 5, 2026 | $54.39–$79.19 typical range · internal point $69.50 | — | ±18.6% | 5/10 | Momentum extends toward DCF anchor zone |
| What actually happened: closed $74.03 on Sep 4, 2026 = +10.8% vs the call (predicted +4.1%) · direction MISS (called flat, was up) · off by 6.8 pp · accuracy 4/10 · typical range ±18.6%: inside the band · S&P -0.1% over the same window — beat it | ||||||
| 2 months | Oct 5, 2026 | $68.00 | — | +1.8% | 4/10 | Sentiment drag begins pulling toward fair value |
| What actually happened: closed $85.03 on Oct 2, 2026 = +27.3% vs the call (predicted +1.8%) · direction MISS (called flat, was up) · off by 25.5 pp · accuracy 3/10 · S&P 0.0% over the same window — beat it | ||||||
| 3 months | Nov 5, 2026 | $66.00 | — | -1.2% | 5/10 | Value gravity toward composite $65.56 anchor |
| 4 months | Dec 5, 2026 | $67.50 | — | +1.1% | 4/10 | Earnings-window volatility; beat streak supports |
| 5 months | Jan 5, 2027 | $68.50 | — | +2.6% | 4/10 | Post-print stabilization near deserved value |
| 6 months | Feb 5, 2027 | $69.00 | — | +3.3% | 4/10 | Converges toward baseline endpoint near $69 |
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 $69.08 (+3.4%) — 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 · 2 degraded · 1 note — follow the chain top-down (cause → effect).-
Degraded
[critical] Revenue is volatile and unreliable — growth projections are speculative
-
Degraded
[critical] AI analysis identifies strong headwinds — multiple forces working against this stock
-
Note
Valuation anchor absent: anchored_pe.
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 | $66.79 |
| Composite fair value | $65.56 |
| Signal-adjusted fair value | $60.72 |
| DCF fair value | $78.70 |
| Anchored-PE fair value | — |
| Buy-below (value lens) | $52.00 |
| Value net score | -38 |
| Value confidence | 7 / 10 |
| Quality net score | +6 |
| 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 53.9% 3m 64.3% 6m 53.1% |
| Daily σ (realism noise) | 4.1% |
| Beta vs S&P 500 | 1m 2.32 3m 1.97 5m 1.54 |
| Trailing 6-month return | 17.5% |
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 | SWKS-20260803-171702-fe33 |
ext-forensic-memo |
Aug 3, 2026 | freshest | ext-SWKS-20260803-180447-98c0 |
ext-lens-quality |
Aug 3, 2026 | freshest | ext-SWKS-20260803-180447-98c0 |
ext-lens-sentiment |
Aug 3, 2026 | freshest | ext-SWKS-20260803-180447-98c0 |
ext-lens-value |
Aug 3, 2026 | freshest | ext-SWKS-20260803-180447-98c0 |
scenario-valuation |
Aug 3, 2026 | freshest | SWKS-20260803-171702-fe33 |
valuation-synthesis |
Aug 3, 2026 | freshest | SWKS-20260803-171702-fe33 |
Inputs flagged 7d+ behind the freshest one may be stale relative to the rest of the analysis.
Saved History
3 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.