Made on
Sep 4, 2026
Price at call
$156.24
6-month call
Bear -9.1%
Target by Mar 2027
$142.00
Great value below
$120.00
Model
v0.6.0
Projection vs Actual (6M history + forecast)
Forecast Change
-9.1% to $142.00
Predicted High
$170.00
at 2 months
Predicted Low
$142.00
at 6 months
Max Drawdown (predicted)
-9.1%
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 4, 2026 1:04 pm
Bear
ROKU trends lower to
$142.00
(-9.1% from $156.24)
by Mar 2027.
ride-then-fade
ThesisROKU is in a live re-rating with strong sentiment (74/100), risk-on regime, and M&A optionality driving momentum into year-end; however, value lens flags overvaluation (attractive below $120) and the stock is 61% up over 6 months, so I expect continued upside near-term that partially fades as gravity reasserts in Q1 2027.
Invalidated ifBreak below $135 support, regime flip to risk-off, or negative pre-announcement would invalidate the continued uptrend thesis.
| Checkpointtime after the call | Datewhen it gets graded | Predictedthe claim: closing price | Current priceactual close — fills in over time | Predicted returnpredicted vs $156.24 at call | Conv.brain's confidence, 1–10 | Driverwhy the brain put the point here |
|---|---|---|---|---|---|---|
| Prediction made | Sep 4, 2026 | — | $156.24 at call | — | — | The anchor — every point below is measured from this price and date. |
| 2 weeks | Sep 18, 2026 | $143.57–$168.91 typical range · internal point $161.50 | — | ±8.1% | 6/10 | Momentum and risk-on tape carry price higher short-term |
| What actually happened: closed $154.08 on Sep 17, 2026 = -1.4% vs the call (predicted +3.4%) · direction HIT (called flat, was flat) · off by 4.8 pp · accuracy 8/10 · typical range ±8.1%: inside the band · S&P -1.1% over the same window — lagged it | ||||||
| 1 month | Oct 4, 2026 | $137.88–$174.60 typical range · internal point $165.00 | — | ±11.8% | 5/10 | Sentiment wave and bullish revisions extend rally |
| 2 months | Nov 4, 2026 | $170.00 | — | +8.8% | 4/10 | Q3 earnings anticipation with 3 of 4 beat history |
| 3 months | Dec 4, 2026 | $168.00 | — | +7.5% | 4/10 | Year-end positioning; some profit-taking on high beta |
| 4 months | Jan 4, 2027 | $158.00 | — | +1.1% | 4/10 | January reset; value gravity begins pulling back |
| 5 months | Feb 4, 2027 | $150.00 | — | -4.0% | 4/10 | Overvaluation concerns weigh as momentum cools |
| 6 months | Mar 4, 2027 | $142.00 | — | -9.1% | 3/10 | Mean reversion toward attractive-below-120 anchor zone |
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 $0.00 (+0.0%) — 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 · 5 notes — follow the chain top-down (cause → effect).-
Degraded
No usable fair-value anchor — brain-only (anchorless) mode: no v0.3 control line, prediction reasons from lenses/sentiment/regime/price behaviour.
-
Note
EPV de-weighted — growth IS the value proposition for this type of company
-
Note
Valuation anchor absent: composite_fair_value.
-
Note
Valuation anchor absent: dcf.
-
Note
Valuation anchor absent: anchored_pe.
-
Note
Valuation anchor absent: signal_adjusted.
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 | $156.24 |
| Composite fair value | — |
| Signal-adjusted fair value | — |
| DCF fair value | — |
| Anchored-PE fair value | — |
| Buy-below (value lens) | — |
| Value net score | -50 |
| Value confidence | 6 / 10 |
| Quality net score | +28 |
| Memo confidence | — / 10 |
| Deserved value (base) | — |
| Quality tilt | — |
| Deserved value (used) | — |
| Coherence (value × quality) | — |
Price behaviour (trailing — shapes the realism line)
| Realized volatility (annualized) | 1m 16.7% 3m 40.7% 6m 41.1% |
| Daily σ (realism noise) | 2.6% |
| Beta vs S&P 500 | 1m 0.42 3m 0.71 5m 1.05 |
| Trailing 6-month return | 61.4% |
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
#8eb3df85c300 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 4, 2026 | freshest | ROKU-20260904-010001-2885 |
ext-forensic-memo |
Sep 4, 2026 | freshest | ext-ROKU-20260904-014823-80a5 |
ext-lens-quality |
Sep 4, 2026 | freshest | ext-ROKU-20260904-014823-80a5 |
ext-lens-sentiment |
Sep 4, 2026 | freshest | ext-ROKU-20260904-014823-80a5 |
ext-lens-value |
Sep 4, 2026 | freshest | ext-ROKU-20260904-014823-80a5 |
scenario-valuation |
Sep 4, 2026 | freshest | ROKU-20260904-010001-2885 |
valuation-synthesis |
Sep 4, 2026 | freshest | ROKU-20260904-010001-2885 |
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 4, 2026 | v0.6.0 | Bear | $156.24 | $142.00 | -9.1% | 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.