Transcript Peer Relative Tone
In plain terms
Strips out industry-wide sentiment and measures only how this firm's call tone differs from peers — 2× the drift of raw tone.
How it works
Frankel-Jennings-Lee (2022 RAST) "Disclosure Sentiment: Machine Learning vs Dictionary Methods": FinBERT-tone residualized against peers in the same industry has 2× the post-earnings drift R² of raw tone. The idea: an absolute tone of +0.2 means very different things for a defensive consumer-staples name (peer baseline ~+0.3) vs an early-stage biotech (peer baseline ~−0.1). Subtracting the peer median isolates firm-specific narrative; long when peer-relative-tone z ≥ +1, short when ≤ −1.
Live results
1 times picked on its own · 3 times inside a blend (3 beat the stock) · updated 2026-06-06Data dependencies
- Daily prices
Adjusted-close OHLCV for every US-listed ticker; primary price feed.
- Transcript finbert scores
A data feed this strategy reads, refreshed on its normal schedule.
Expected edge
- Tested over
- 2002-2020 (Frankel-Jennings-Lee)
See the source research for the original effect size; a modern replication on new data may be weaker.
Explore Transcript Peer Relative Tone on alphactor.ai
See which tickers this family is currently firing on, with live signals and rankings.