Made on
Jul 31, 2026
Price at call
$34.36
6-month call
Bear -5.4%
Target by Jan 2027
$32.50
Model
v0.6.0
Projection vs Actual (6M history + forecast)
Forecast Change
-5.4% to $32.50
Predicted High
$35.60
at 1 month
Predicted Low
$32.50
at 6 months
Max Drawdown (predicted)
-5.4%
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 31, 2026 2:08 am
Bear
EXLS trends lower to
$32.50
(-5.4% from $34.36)
by Jan 2027.
ride-then-fade
ThesisEXLS just delivered a Q2 beat, raised guide, and announced an AI acquisition, igniting momentum on a normally quiet name. Sentiment carries the stock modestly higher near-term, but valuation anchors below current price and negative beta pull it back toward fair value as the news fades over months.
Invalidated ifA close below $30 in the first month, or a guidance cut, would invalidate the ride-then-fade path.
| Checkpointtime after the call | Datewhen it gets graded | Predictedthe claim: closing price | Current priceactual close — fills in over time | Predicted returnpredicted vs $34.36 at call | Conv.brain's confidence, 1–10 | Driverwhy the brain put the point here |
|---|---|---|---|---|---|---|
| Prediction made | Jul 31, 2026 | — | $34.36 at call | — | — | The anchor — every point below is measured from this price and date. |
| 2 weeks | Aug 14, 2026 | $30.62–$38.10 typical range · internal point $35.20 | — | ±10.9% | 7/10 | Post-beat sentiment momentum carries tape higher near-term |
| What actually happened: closed $35.37 on Aug 13, 2026 = +2.9% vs the call (predicted +2.4%) · direction HIT (called flat, was flat) · off by 0.5 pp · accuracy 10/10 · typical range ±10.9%: inside the band · S&P +4.1% over the same window — beat it | ||||||
| 1 month | Aug 31, 2026 | $28.94–$39.78 typical range · internal point $35.60 | — | ±15.8% | 6/10 | AI acquisition narrative sustains bid, buyers still active |
| 2 months | Oct 1, 2026 | $34.80 | — | +1.3% | 5/10 | Momentum cools as no new catalyst; drift begins |
| 3 months | Oct 31, 2026 | $33.90 | — | -1.3% | 5/10 | Pre-earnings positioning, valuation gravity starts pulling |
| 4 months | Dec 1, 2026 | $33.20 | — | -3.4% | 4/10 | Fair value convergence toward signal-adjusted anchor |
| 5 months | Dec 31, 2026 | $32.80 | — | -4.5% | 4/10 | Year-end tax selling on laggard, anchors dominate |
| 6 months | Jan 31, 2027 | $32.50 | — | -5.4% | 4/10 | Settles near DCF and anchored-PE fair value range |
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 $34.33 (-0.1%) — 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 | $34.36 |
| Composite fair value | $28.02 |
| Signal-adjusted fair value | $33.15 |
| DCF fair value | $32.01 |
| Anchored-PE fair value | $32.76 |
| Buy-below (value lens) | — |
| Value net score | -35 |
| Value confidence | 7 / 10 |
| Quality net score | +70 |
| Memo confidence | 6 / 10 |
| Deserved value (base) | — |
| Quality tilt | — |
| Deserved value (used) | — |
| Coherence (value × quality) | — |
Price behaviour (trailing — shapes the realism line)
| Realized volatility (annualized) | 1m 70.1% 3m 54.6% 6m 53.6% |
| Daily σ (realism noise) | 3.4% |
| Beta vs S&P 500 | 1m -3.41 3m -1.33 5m -0.57 |
| Trailing 6-month return | -13.6% |
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 30, 2026 | freshest | EXLS-20260730-193529-4840 |
ext-forensic-memo |
Jul 30, 2026 | freshest | ext-EXLS-20260730-205959-74df |
ext-lens-quality |
Jul 30, 2026 | freshest | ext-EXLS-20260730-205959-74df |
ext-lens-sentiment |
Jul 30, 2026 | freshest | ext-EXLS-20260730-205959-74df |
ext-lens-value |
Jul 30, 2026 | freshest | ext-EXLS-20260730-205959-74df |
scenario-valuation |
Jul 30, 2026 | freshest | EXLS-20260730-193529-4840 |
valuation-synthesis |
Jul 30, 2026 | freshest | EXLS-20260730-205438-85b4 |
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 | |
|---|---|---|---|---|---|---|---|
| Jul 31, 2026 | v0.6.0 | Bear | $34.36 | $32.50 | -5.4% | 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.