Text-NLPtier 1live in production
transcript text features
cadence: Annualdata: low
JF
2011
Journal of Finance
We use a small curated subset of Loughran-McDonald (2011) finance dict
Citation only — paper link pending.
Mechanism
We use a small curated subset of Loughran-McDonald (2011) finance dict plus a few standard modal markers. Full LM dict has ~4k words; this ~300-word subset captures the high-signal common cases without bloating the package. If we want production-grade LM scoring, drop a CSV of the full dictionary in `services/worker/data/loughran_mcdonald.csv` and swap `_load_lm_terms()` to…
Data dependencies
Standard universe pricing only.
Expected edge
See referenced paper for original effect size; modern out-of-sample replication may be weaker.
Illustrative pattern only
NOT a backtestIllustrative pattern only — see /app for live backtests and the actual current equity curve.
Explore transcript text features on alphactor.ai
See which tickers this family is currently firing on, with live signals and rankings.