Made on
Jul 22, 2026
Price at call
$113.05
6-month call
Bear -9.8%
Target by Jan 2027
$102.00
Great value below
$88.00
Model
v0.6.0
Projection vs Actual (6M history + forecast)
Forecast Change
-9.8% to $102.00
Predicted High
$119.00
at 1 month
Predicted Low
$102.00
at 6 months
Max Drawdown (predicted)
-9.8%
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 6:13 am
Bear
EBAY trends lower to
$102.00
(-9.8% from $113.05)
by Jan 2027.
ride-then-fade
ThesisCohen's 10% stake and takeover chatter dominate near-term action, with the Aug 5 earnings print (8-of-8 beat streak) likely reinforcing bullish sentiment. Over months, valuation gravity from a composite fair value near $36 pulls the stock down, but activist support and buyback capacity limit the descent well above deterministic fair value.
Invalidated ifCohen exits the position, or an earnings miss breaks the 8-quarter streak, or shares break below $95 support on heavy volume.
| Checkpointtime after the call | Datewhen it gets graded | Predictedthe claim: closing price | Current priceactual close — fills in over time | Predicted returnpredicted vs $113.05 at call | Conv.brain's confidence, 1–10 | Driverwhy the brain put the point here |
|---|---|---|---|---|---|---|
| Prediction made | Jul 22, 2026 | — | $113.05 at call | — | — | The anchor — every point below is measured from this price and date. |
| 2 weeks | Aug 5, 2026 | $105.84–$120.26 typical range · internal point $117.50 | — | ±6.4% | 6/10 | Earnings beat streak plus activist bid keeps momentum |
| What actually happened: closed $109.61 on Aug 4, 2026 = -3.0% vs the call (predicted +3.9%) · direction HIT (called flat, was flat) · off by 7.0 pp · accuracy 7/10 · typical range ±6.4%: inside the band · S&P +3.2% over the same window — lagged it | ||||||
| 1 month | Aug 22, 2026 | $102.60–$123.50 typical range · internal point $119.00 | — | ±9.2% | 5/10 | Post-earnings drift, Cohen headlines sustain premium |
| What actually happened: closed $104.11 on Aug 21, 2026 = -7.9% vs the call (predicted +5.3%) · direction MISS (called up, was down) · off by 13.2 pp · accuracy 4/10 · typical range ±9.2%: inside the band · S&P +2.3% over the same window — lagged it | ||||||
| 2 months | Sep 22, 2026 | $115.00 | — | +1.7% | 5/10 | Activist narrative cools, valuation questions resurface |
| 3 months | Oct 22, 2026 | $110.00 | — | -2.7% | 5/10 | Q3 print looms, sentiment tailwind fades gradually |
| 4 months | Nov 22, 2026 | $107.00 | — | -5.3% | 4/10 | Value gravity asserts as takeover urgency dims |
| 5 months | Dec 22, 2026 | $104.00 | — | -8.0% | 4/10 | Year-end positioning, rich multiple weighs on shares |
| 6 months | Jan 22, 2027 | $102.00 | — | -9.8% | 4/10 | Drift toward deterministic baseline as story stales |
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 $100.27 (-11.3%) — 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 · 1 degraded · 2 notes — follow the chain top-down (cause → effect).-
Degraded
Valuation is extremely fragile — almost no scenarios support the current price
-
Note
Valuation anchor absent: dcf.
-
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 | $113.05 |
| Composite fair value | $35.78 |
| Signal-adjusted fair value | $32.67 |
| DCF fair value | — |
| Anchored-PE fair value | — |
| Buy-below (value lens) | $88.00 |
| Value net score | -48 |
| Value confidence | 5 / 10 |
| Quality net score | +36 |
| 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 27.9% 3m 32.0% 6m 34.6% |
| Daily σ (realism noise) | 2.0% |
| Beta vs S&P 500 | 1m -0.12 3m 0.22 5m 0.56 |
| Trailing 6-month return | 21.5% |
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 | EBAY-20260722-030001-c4a4 |
ext-forensic-memo |
Jul 22, 2026 | freshest | ext-EBAY-20260722-055558-4790 |
ext-lens-quality |
Jul 22, 2026 | freshest | ext-EBAY-20260722-055558-4790 |
ext-lens-sentiment |
Jul 22, 2026 | freshest | ext-EBAY-20260722-055558-4790 |
ext-lens-value |
Jul 22, 2026 | freshest | ext-EBAY-20260722-055558-4790 |
scenario-valuation |
Jul 22, 2026 | freshest | EBAY-20260722-030001-c4a4 |
valuation-synthesis |
Jul 22, 2026 | freshest | EBAY-20260722-030001-c4a4 |
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 18, 2026 | v0.6.0 | Bear | $100.94 | $87.00 | -13.8% | Feb 2027 | view |
| Jul 22, 2026 | v0.6.0 | Bear | $113.05 | $102.00 | -9.8% | 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.