Made on
Jul 22, 2026
Price at call
$78.72
6-month call
Bear -8.2%
Target by Jan 2027
$72.30
Great value below
$66.00
Model
v0.6.0
Projection vs Actual (6M history + forecast)
Forecast Change
-8.2% to $72.30
Predicted High
$78.90
in 2 weeks
Predicted Low
$72.30
at 6 months
Max Drawdown (predicted)
-8.2%
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 Jul 22, 2026 6:23 am
Bear
XEL trends lower to
$72.30
(-8.2% from $78.72)
by Jan 2027.
ride-then-fade
ThesisXEL trades meaningfully above composite fair value ($65) with weak value/quality lenses, but a durable low-beta utility narrative and analyst tailwind cushion downside. Expect near-term earnings-driven volatility, then a slow drift toward the deterministic $72 endpoint as valuation gravity works.
Invalidated ifA clear earnings beat with raised guidance pushing shares above $82, or conversely a break below $74 on rate shock, would invalidate the gradual-fade path.
| Checkpointtime after the call | Datewhen it gets graded | Predictedthe claim: closing price | Current priceactual close — fills in over time | Predicted returnpredicted vs $78.72 at call | Conv.brain's confidence, 1–10 | Driverwhy the brain put the point here |
|---|---|---|---|---|---|---|
| Prediction made | Jul 22, 2026 | — | $78.72 at call | — | — | The anchor — every point below is measured from this price and date. |
| 2 weeks | Aug 5, 2026 | $75.18–$82.26 typical range · internal point $78.90 | — | ±4.5% | 5/10 | Earnings print inside window, mixed beat history |
| What actually happened: closed $77.75 on Aug 4, 2026 = -1.2% vs the call (predicted +0.2%) · direction HIT (called flat, was flat) · off by 1.5 pp · accuracy 10/10 · typical range ±4.5%: inside the band · S&P +3.2% over the same window — beat it | ||||||
| 1 month | Aug 22, 2026 | $73.58–$83.86 typical range · internal point $78.20 | — | ±6.5% | 5/10 | Post-earnings digestion, sentiment still supportive |
| What actually happened: closed $76.31 on Aug 21, 2026 = -3.1% vs the call (predicted -0.7%) · direction HIT (called flat, was flat) · off by 2.4 pp · accuracy 9/10 · typical range ±6.5%: inside the band · S&P +2.3% over the same window — beat it | ||||||
| 2 months | Sep 22, 2026 | $77.10 | — | -2.1% | 5/10 | Valuation gravity begins, low-beta drift |
| 3 months | Oct 22, 2026 | $75.60 | — | -4.0% | 5/10 | Rate sensitivity, fair-value pull intensifies |
| 4 months | Nov 22, 2026 | $74.20 | — | -5.7% | 4/10 | Continued mean reversion toward anchored PE |
| 5 months | Dec 22, 2026 | $73.10 | — | -7.1% | 4/10 | Year-end tax positioning, defensive bid softens |
| 6 months | Jan 22, 2027 | $72.30 | — | -8.2% | 4/10 | Converges near 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 $72.09 (-8.4%) — 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 · 3 degraded · 1 note — follow the chain top-down (cause → effect).-
Degraded
Cash flow quality is poor — reported earnings may not reflect reality
-
Degraded
High debt risk — interest coverage dangerously low or refinancing needed
-
Degraded
Valuation is extremely fragile — almost no scenarios support the current price
-
Note
Valuation anchor absent: dcf.
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 | $78.72 |
| Composite fair value | $65.18 |
| Signal-adjusted fair value | $61.59 |
| DCF fair value | — |
| Anchored-PE fair value | $66.38 |
| Buy-below (value lens) | $66.00 |
| Value net score | -78 |
| Value confidence | 7 / 10 |
| Quality net score | -29 |
| Memo confidence | 8 / 10 |
| Deserved value (base) | — |
| Quality tilt | — |
| Deserved value (used) | — |
| Coherence (value × quality) | — |
Price behaviour (trailing — shapes the realism line)
| Realized volatility (annualized) | 1m 20.4% 3m 22.6% 6m 20.8% |
| Daily σ (realism noise) | 1.4% |
| Beta vs S&P 500 | 1m -0.73 3m -0.11 5m 0.01 |
| Trailing 6-month return | 4.1% |
Knobs (equation params)
| ladder | Array |
| llm_model | claude-opus-4-7 |
| max_tokens | 3000 |
| control_knobs | Array |
| 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 22, 2026 | freshest | XEL-20260722-030001-80a5 |
ext-forensic-memo |
Jul 22, 2026 | freshest | ext-XEL-20260722-055558-1b5c |
ext-lens-quality |
Jul 22, 2026 | freshest | ext-XEL-20260722-055558-1b5c |
ext-lens-sentiment |
Jul 22, 2026 | freshest | ext-XEL-20260722-055558-1b5c |
ext-lens-value |
Jul 22, 2026 | freshest | ext-XEL-20260722-055558-1b5c |
valuation-synthesis |
Jul 22, 2026 | freshest | XEL-20260722-030001-80a5 |
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 17, 2026 | v0.6.0 | Neutral | $79.17 | $75.50 | -4.6% | Feb 2027 | view |
| Jul 22, 2026 | v0.6.0 | Bear | $78.72 | $72.30 | -8.2% | Jan 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.