COLL
← full report
Collegium Pharmaceutical Inc.
Healthcare · Drug Manufacturers - Specialty & Generic
Made on
Jul 31, 2026
Price at call
$35.98
6-month call
Bull +25.1%
Target by Jan 2027
$45.00
Great value below
$32.00
Model
v0.6.0
Projection vs Actual (6M history + forecast)
Forecast Change
+25.1% to $45.00
Predicted High
$45.00
at 6 months
Predicted Low
$34.50
at 2 months
Max Drawdown (predicted)
-4.1%
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 Jul 31, 2026 2:08 am
Bull
COLL trends higher to
$45.00
(+25.1% from $35.98)
by Jan 2027.
dip-then-recover
ThesisCOLL trades at a deep discount to intrinsic value estimates but carries opioid-related stigma and weak recent momentum. Value gravity should pull higher over 6 months, but the deterministic 240% surge is unrealistic without a catalyst; expect gradual re-rating with sentiment tailwind supporting a moderate climb.
Invalidated ifBreak below $32 sustained, or DEA/regulatory action on Jornay/opioid franchise, would invalidate the recovery thesis.
| Checkpointtime after the call | Datewhen it gets graded | Predictedthe claim: closing price | Current priceactual close — fills in over time | Predicted returnpredicted vs $35.98 at call | Conv.brain's confidence, 1–10 | Driverwhy the brain put the point here |
|---|---|---|---|---|---|---|
| Prediction made | Jul 31, 2026 | — | $35.98 at call | — | — | The anchor — every point below is measured from this price and date. |
| 2 weeks | Aug 14, 2026 | $33.20–$38.76 typical range · internal point $36.40 | — | ±7.7% | 6/10 | Momentum tailwind persists in quiet neutral tape |
| What actually happened: closed $28.15 on Aug 13, 2026 = -21.8% vs the call (predicted +1.2%) · direction MISS (called flat, was down) · off by 22.9 pp · accuracy 3/10 · typical range ±7.7%: OUTSIDE the band · S&P +4.1% over the same window — beat it | ||||||
| 1 month | Aug 31, 2026 | $31.94–$40.02 typical range · internal point $35.20 | — | ±11.2% | 5/10 | Mild pullback toward attractive-below level |
| 2 months | Oct 1, 2026 | $34.50 | — | -4.1% | 4/10 | Consolidation near value zone before earnings window |
| 3 months | Oct 31, 2026 | $37.50 | — | +4.2% | 5/10 | Q3 print potential lifts sentiment modestly |
| 4 months | Dec 1, 2026 | $40.00 | — | +11.2% | 5/10 | Value recognition begins as discount narrows |
| 5 months | Dec 31, 2026 | $42.50 | — | +18.1% | 4/10 | Year-end positioning into deep-value name |
| 6 months | Jan 31, 2027 | $45.00 | — | +25.1% | 4/10 | Continued re-rating 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 $122.26 (+239.8%) — 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 · 0 degraded · 1 note — follow the chain top-down (cause → effect).-
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 | $35.98 |
| Composite fair value | $210.87 |
| Signal-adjusted fair value | $272.51 |
| DCF fair value | $291.26 |
| Anchored-PE fair value | — |
| Buy-below (value lens) | $32.00 |
| Value net score | +43 |
| Value confidence | 6 / 10 |
| Quality net score | +55 |
| 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 30.2% 3m 38.9% 6m 38.6% |
| Daily σ (realism noise) | 2.4% |
| Beta vs S&P 500 | 1m 0.15 3m -0.32 5m 0.39 |
| Trailing 6-month return | -19.7% |
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 | COLL-20260730-194007-7eaa |
ext-forensic-memo |
Jul 30, 2026 | freshest | ext-COLL-20260730-211424-766d |
ext-lens-quality |
Jul 30, 2026 | freshest | ext-COLL-20260730-211424-766d |
ext-lens-sentiment |
Jul 30, 2026 | freshest | ext-COLL-20260730-211424-766d |
ext-lens-value |
Jul 30, 2026 | freshest | ext-COLL-20260730-211424-766d |
scenario-valuation |
Jul 30, 2026 | freshest | COLL-20260730-205438-5258 |
valuation-synthesis |
Jul 30, 2026 | freshest | COLL-20260730-205438-5258 |
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 | Bull | $35.98 | $45.00 | +25.1% | 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.