Patent Class Drift
In plain terms
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.
How it works
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).
Live results
0 times picked on its own · 13 times inside a blend (13 beat the stock) · updated 2026-07-06Data dependencies
- Patents
USPTO grant data with citation counts.
- Daily prices
Adjusted-close OHLCV for every US-listed ticker; primary price feed.
Expected edge
- Reported return
- 7-9% ann. over 1-2y holding
- Tested over
- 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
Markets under-react when companies are granted high-value patents (measured by 3-day stock reaction at grant). Firms with valuable recent patents outperform by 3-5%/yr.
Standard value factors mistake R&D-heavy tech firms as 'growth' because R&D is expensed not capitalized. Adding R&D back uncovers hidden value.
Counts AI/LLM phrases in each earnings call and trades firms whose AI talk jumps (long) or fades (short) versus their own history. Inspired by the finding that AI-exposed firms outperformed sharply after ChatGPT launched, but built from call transcripts rather than the paper's workforce data.
Explore Patent Class Drift on alphactor.ai
See which tickers this family is currently firing on, with live signals and rankings.