Made on
Aug 29, 2026
Price at call
$114.80
6-month call
Neutral +3.2%
Target by Mar 2027
$118.50
Great value below
$92.00
Model
v0.6.0
Projection vs Actual (6M history + forecast)
Forecast Change
+3.2% to $118.50
Predicted High
$118.50
at 6 months
Predicted Low
$112.00
at 1 month
Max Drawdown (predicted)
-2.4%
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 Aug 29, 2026 1:05 pm
Neutral
EPAM trends range-bound to
$118.50
(+3.2% from $114.80)
by Mar 2027.
dip-then-recover
ThesisEPAM sits near composite fair value with a recent JPM downgrade and negative 6-month drift capping upside near-term, but consistent EPS beats and a risk-on tape support a slow drift back toward the $117 DCF anchor over six months.
Invalidated ifA break below $100 on heavy volume or a guide-down would falsify; conversely a sustained move above $125 without earnings catalyst suggests stronger re-rating.
| Checkpointtime after the call | Datewhen it gets graded | Predictedthe claim: closing price | Current priceactual close — fills in over time | Predicted returnpredicted vs $114.80 at call | Conv.brain's confidence, 1–10 | Driverwhy the brain put the point here |
|---|---|---|---|---|---|---|
| Prediction made | Aug 29, 2026 | — | $114.80 at call | — | — | The anchor — every point below is measured from this price and date. |
| 2 weeks | Sep 12, 2026 | $99.92–$129.68 typical range · internal point $113.50 | — | ±13.0% | 6/10 | JPM downgrade weight and weak momentum persist short-term |
| What actually happened: closed $117.91 on Sep 11, 2026 = +2.7% vs the call (predicted -1.1%) · direction HIT (called flat, was flat) · off by 3.8 pp · accuracy 9/10 · typical range ±13.0%: inside the band · S&P -0.7% over the same window — lagged it | ||||||
| 1 month | Sep 29, 2026 | $93.24–$136.36 typical range · internal point $112.00 | — | ±18.8% | 5/10 | Sentiment drag continues absent catalysts |
| What actually happened: closed $107.55 on Sep 28, 2026 = -6.3% vs the call (predicted -2.4%) · direction MISS (called flat, was down) · off by 3.9 pp · accuracy 4/10 · typical range ±18.8%: inside the band · S&P -0.4% over the same window — beat it | ||||||
| 2 months | Oct 29, 2026 | $115.00 | — | +0.2% | 5/10 | Q3 earnings anticipation, prior beats support drift up |
| 3 months | Nov 29, 2026 | $118.00 | — | +2.8% | 6/10 | Post-earnings beat lifts toward DCF anchor |
| 4 months | Dec 29, 2026 | $117.00 | — | +1.9% | 5/10 | Year-end consolidation near fair value |
| 5 months | Jan 29, 2027 | $116.00 | — | +1.0% | 4/10 | January tape digestion, value gravity holds |
| 6 months | Mar 1, 2027 | $118.50 | — | +3.2% | 4/10 | Gradual convergence toward composite fair value |
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 $116.97 (+1.9%) — 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 | $114.80 |
| Composite fair value | $116.18 |
| Signal-adjusted fair value | $108.06 |
| DCF fair value | $117.69 |
| Anchored-PE fair value | $147.55 |
| Buy-below (value lens) | $92.00 |
| Value net score | -21 |
| Value confidence | 7 / 10 |
| Quality net score | +16 |
| 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 70.3% 3m 65.1% 6m 53.3% |
| Daily σ (realism noise) | 4.1% |
| Beta vs S&P 500 | 1m 1.58 3m -0.07 5m -0.24 |
| Trailing 6-month return | -18.5% |
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 | 25d behind | EPAM-20260803-164946-600b |
ext-forensic-memo |
Aug 29, 2026 | freshest | ext-EPAM-20260829-012333-a000 |
ext-lens-quality |
Aug 29, 2026 | freshest | ext-EPAM-20260829-012333-a000 |
ext-lens-sentiment |
Aug 29, 2026 | freshest | ext-EPAM-20260829-012333-a000 |
ext-lens-value |
Aug 29, 2026 | freshest | ext-EPAM-20260829-012333-a000 |
scenario-valuation |
Aug 29, 2026 | freshest | EPAM-20260829-010001-dc28 |
valuation-synthesis |
Aug 29, 2026 | freshest | EPAM-20260829-010001-dc28 |
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 29, 2026 | v0.6.0 | Neutral | $114.80 | $118.50 | +3.2% | Mar 2027 | viewing |
| Aug 4, 2026 | v0.6.0 | Bull | $107.26 | $120.00 | +11.9% | Feb 2027 | view |
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.