patent class drift
What it checks
When a company's patent portfolio shifts into new technology classes (e.g. legacy hardware -> AI), it's signaling a real pivot. The stock outperforms over the next 1-2 years.
Mechanism
Cohen-Diether-Malloy 2013 RFS document that firms reallocating R&D / patent filings toward different technology classes earn 7-9% ann. abnormal returns over 1-2y. The market under-weights narrative pivots — patent-class shifts signal a real business reorientation that sell-side estimates don't reflect in real time. We proxy class-pivot via the rolling z-score of KPSS monthly innovation-value (highly correlated with the class-entropy delta in the paper's appendix).
Signal rule
12mo rolling z of monthly patent_innovation_value; long on positive spike + 60d uptrend (pivot to higher-value classes), short on negative spike + 60d downtrend.
Data dependencies
patentsUSPTO grant data with citation counts.
daily_pricesAdjusted-close OHLCV for every US-listed ticker; primary price feed.
Expected edge
- Paper alpha
- 7-9% ann. over 1-2y holding
- Paper window
- 1985-2010
Cohen-Diether-Malloy 2013: 7-9% ann. long-pivot-up / short-pivot-down spread over 1-2y.
Example tickers where this is likely to fire
Illustrative only — the signal fires based on the live data, not a fixed list.
Related families
patent innovation premiumNetwork-EffectsPatent values inferred from 3-day stock reaction to USPTO grant. Firms with high value of recently granted patents (relative to market cap) outperform by ~3-5%/yr — real options on growth the market under-prices until citations validate.
rd capitalized valueAccountingStandard book-to-market based value factors mis-classify R&D-heavy firms as "growth" because R&D is expensed (not capitalized) under GAAP. Peters-Taylor 2017 + Eisfeldt-Kim-Papanikolaou 2020 show that adding capitalized R&D back to book equity restores the value premium for tech/biotech and reverses the apparent "value-is-dead" finding of the 2010s. We compute an R&D-intensity metric per ticker and overweight it when it's accompanied by a price drawdown — the intangibles-implied value play.
transcript ai exposureText-NLPEisfeldt-Schubert-Zhang (2023) NBER w31222 "Generative AI and Firm Values": HHVT-style bigram score against an AI/LLM training corpus (ChatGPT-era ML papers + tech-press articles). Documented a 5-month L/S of ~9% post Nov-2022 on the AI-exposure decile — the cleanest paper-published AI-narrative trade in the literature. Signal is own-history z of per-call AI-bigram density: long when z ≥ +1 (firm just elevated AI narrative), short when z ≤ −1 (firm de-emphasized AI).
Explore patent class drift on alphactor.ai
See which tickers this family is currently firing on, with live signals and rankings.