What is a PDUFA date?

A PDUFA (Prescription Drug User Fee Act) date is the FDA's target action date for making a regulatory decision on a drug application (NDA or BLA). These dates are critical binary events for biotech investors as they can cause significant stock price movements of 20-70% in either direction.

How does ODIN predict FDA approvals?

ODIN v14 is a 51-feature L2 Ridge regression trained on 2,210 historical FDA PDUFA events (705 CRLs, 32.0% base rate) from 2015-2026. It analyzes signals across regulatory designations, manufacturing risk, therapeutic area history, sponsor experience, clinical trial design, and FDA era effects to produce a calibrated approval probability. It achieves 0.9363 AUC on walk-forward testing with consistent yearly performance (0.89-0.94).

What is the PDUFA runup strategy?

The PDUFA runup strategy is a validated trading approach based on analysis of 934 PDUFA events showing that biotech stocks systematically appreciate in the 25 trading days before an FDA decision date. The strategy enters at T-25 and exits at T-5 or T-7 depending on ODIN tier, capturing the anticipatory move without holding through the binary event.

ODIN assigns each FDA catalyst to one of four conviction tiers: TIER_1 (85%+ approval probability, full position), TIER_2 (65-85%, half position), TIER_3 (40-65%, small speculative or avoid), and TIER_4 (below 40%, no trade). The tiers drive position sizing and risk management for the PDUFA runup trading strategy.

What is a Complete Response Letter (CRL)?

A Complete Response Letter (CRL) is an FDA notification that the agency cannot approve a drug application in its current form. CRLs cite deficiencies in manufacturing (CMC), clinical efficacy, or safety data. Historically, 32.3% of PDUFA decisions result in CRLs. ODIN's strongest signal is prior CRL history, which carries a -3.21 logit penalty.

When was ETON Pharmaceuticals topical baclofen PDUFA date?

ETON Pharmaceuticals topical baclofen had a PDUFA target action date of February 25, 2026. The FDA approved the drug on schedule on February 25, 2026. ODIN scored it at 85.5% TIER_1, and the stock rose +14.7% during the runup from T-25 to T-7. Track live PDUFA status and ODIN AI approval probability (AUC 0.9363) at pdufa.bio/eton-pdufa.

What is the Vanda Pharmaceuticals PDUFA date in February 2026?

Vanda Pharmaceuticals (VNDA) had a PDUFA target action date of February 21, 2026 for Bysanti (milsaperidone) for schizophrenia. The FDA approved the drug one day early on February 20, 2026. ODIN scored it at 89.7% TIER_1, and the stock rose +44% after hours. Track live PDUFA status and ODIN AI approval probability (AUC 0.9363) at pdufa.bio/calendar.

What are the upcoming PDUFA dates for February 2026?

Key February 2026 PDUFA dates include ETON Topical Baclofen (Feb 25, APPROVED), VNDA Bysanti (Feb 21, APPROVED), OTSKF INQOVI+Venetoclax for AML (Feb 25), REGN Dupixent for allergic fungal rhinosinusitis (Feb 28, APPROVED), and ASND Navepegritide for anemia of CKD (Feb 28). The full Q1 2026 calendar with ODIN AI biotech catalyst scores is available at pdufa.bio/pdufa-calendar-2026.

What FDA approvals are expected in Q1 2026?

Q1 2026 features approximately 10-12 FDA PDUFA decisions, including high-profile oncology, immunology, and endocrinology catalysts. Key names include BMY deucravacitinib for UC (March 6), LLY orforglipron for diabetes (April 10), RCKT Kresladi gene therapy (March 28), and LNTH Ga68-edotreotide for NET imaging (March 29). Track all dates with ODIN probability scores at pdufa.bio.

What is the ODIN engine and how accurate is it?

ODIN is a 51-feature L2 Ridge regression trained on 2,210 historical FDA events. It achieves 0.9363 AUC on walk-forward testing across 5 yearly folds. It predicts the probability of FDA approval for each PDUFA event using gradient-boosted decision trees across 8 signal categories.

What data does ODIN use?

ODIN analyzes regulatory designations (Breakthrough, Fast Track, Priority Review), manufacturing risk, therapeutic area history, sponsor track record, clinical trial design quality, prior CRL history, FDA era effects, and advisory committee recommendations. All signals are quantified and weighted.

What are the ODIN tiers?

TIER_1: 85%+ probability. TIER_2: 65–85%. TIER_3: 40–65%. TIER_4: <40%. Tiers help investors filter catalysts by confidence level and risk tolerance. Higher tiers correlate with positive stock moves post-approval.

ODIN Scoring Engine

ODIN is a machine learning model that predicts FDA approval probability for biotech catalysts. Built on 2,210 historical FDA events, ODIN achieves 0.9363 AUC on walk-forward backtesting across 5 yearly folds (0.89–0.94 range). It identifies the most likely winners before they happen.

Instead of reading regulatory documents manually, ODIN automatically scores each PDUFA event across 51 features spanning 8 signal categories. Higher ODIN scores correlate with positive stock performance post-approval and larger expected moves.

Methodology & Accuracy

Training Events

2,210

Model Type

L2 Ridge (v14)

Features

Holdout AUC

0.9363

Brier Score

0.0895

Update Frequency

Daily

ODIN v14 uses L2-regularized logistic regression (Ridge, C=0.10) with 51 engineered features to predict binary FDA outcomes (approval / CRL). Trained on 2,210+ historical decisions (2000–2025), covering NDA, BLA, sBLA, and sNDA across all therapeutic areas. Holdout testing on 358 unseen events validates 0.9363 AUC with a T1 win rate of 98.7%, confirming production-grade predictive power.

8 Signal Categories

Signal Category	Description	Weight Impact
Regulatory Designations	Breakthrough Therapy, Fast Track, Priority Review, Accelerated Approval	High
Manufacturing/CMC Risk	Drug substance, drug product, analytical methods, quality assurance issues	Medium
Therapeutic Area History	Historical approval rates in oncology, rare disease, immunology, etc.	High
Sponsor Track Record	Company's historical approval rate, CRL frequency, regulatory responsiveness	Very High
Clinical Trial Design	Efficacy endpoints, safety profile, comparator arms, patient population	Very High
Prior CRL History	Completeness Response Letter issues, deficiencies, safety flags	High
FDA Era Effects	CDER commissioner tenure, regulatory environment, macro policy changes	Low–Medium
Advisory Committee Signals	AdCom vote outcome, questions asked, dissenting votes, sentiment	Medium

ODIN Tier Definitions

TIER_1

85%+ approval probability

High conviction approval. Strong trial data, solid sponsor track record, favorable regulatory path. Expected positive stock reaction.

TIER_2

65–85% approval probability

Moderate–high conviction. Good data but some concerns (e.g., safety signals, competitive landscape). Likely approval.

TIER_3

40–65% approval probability

Moderate conviction. Mixed data, unclear regulatory stance, or higher risk profile. Approval is possible but not favored.

TIER_4

<40% approval probability

Low conviction. Significant concerns (weak efficacy, manufacturing risk, sponsor track record). Approval unlikely.

How ODIN Works

Data Collection: ODIN ingests regulatory filings, clinical trial results, FDA meeting minutes, advisory committee votes, and sponsor company data.
Feature Engineering: 51 features are derived from the 8 signal categories. Each feature is selected and weighted by the L2 Ridge regression based on historical predictive power.
L2 Ridge Regression: The trained gradient-boosted model outputs a calibrated probability score (0–100%) for each PDUFA event. Scores reflect the likelihood of FDA approval.
Tier Classification: Scores are binned into TIER_1 (85%+), TIER_2 (65–85%), TIER_3 (40–65%), TIER_4 (<40%).
Daily Updates: ODIN rescores all pending events nightly as new clinical data, regulatory designations, and company news arrive.

Frequently Asked Questions

How much does a higher ODIN score improve stock returns?

Historical backtesting shows TIER_1 events (85%+ ODIN scores) average +8–12% positive returns post-approval. TIER_2 averages +3–7%. TIER_3 and below show mixed results. Higher ODIN confidence correlates with larger expected moves.

Can ODIN predict rejections as well as approvals?

Yes. ODIN's 0.9363 holdout AUC measures performance across both approval and rejection predictions. Low TIER_4 scores (below 40%) identify high-risk rejections. When ODIN flags TIER_4, rejection probability exceeds 60%, useful for shorting strategies.

How often does ODIN get it wrong?

On holdout data (358 unseen events), ODIN achieves 0.9363 AUC. T1 predictions have a 98.7% win rate across 154 picks. Errors tend to come from T2/T3 events near decision boundaries — the model is calibrated to be most accurate where conviction is highest.