transcript numerical specificity
What it checks
When management gives unusually concrete numbers on an earnings call, uncertainty can fall. When the call gets vague, that can be a warning sign.
Mechanism
More quantitative earnings-call disclosure can reduce information risk. The family counts numeric tokens per 1,000 transcript words and compares each call to the firm's prior call history.
Signal rule
Numeric-token density own-history z-score: long unusually specific calls, short unusually vague calls, T+1 entry, hold 3/21/63d.
Data dependencies
daily_pricesAdjusted-close OHLCV for every US-listed ticker; primary price feed.
earnings_call_transcriptsFull earnings-call transcripts (prepared + Q&A), tokenised.
Expected edge
- Paper alpha
- 23bps 3-day CAR per 1sd numeric specificity in the paper setting
- Paper window
- Earnings-call event windows
Information-risk reduction around number-dense calls.
Example tickers where this is likely to fire
Illustrative only, the signal fires based on the live data, not a fixed list.
Related families
forward looking statement countText & FilingsForward-looking statement (FLS) lexicon density on 10-K MD&A (Item 7) is a predictor of forward-realized volatility and information environment quality. Falling FLS density -> guidance withdrawn -> SHORT; rising -> confident communication -> LONG.
transcript qa combativenessText & FilingsHollander-Pronk-Roelofsen 2010 + Matsumoto-Pronk-Roelofsen 2011: longer analyst questions + lower management answer/question word-count ratios signal skepticism and predict near-term underperformance. Two per-call features: avg_analyst_q_len (tokens per analyst turn) and mgmt_response_ratio (CEO/CFO tokens / analyst tokens). z-score within own history; SHORT when current call's combativeness z > 1.0 (84th percentile). Long leg disabled because positive responses are noisy (good news makes execs talkative).
Explore transcript numerical specificity on alphactor.ai
See which tickers this family is currently firing on, with live signals and rankings.