Text-NLP#89tier 1live in productionNew

transcript cfo qa defensiveness

cadence: Eventdata: mediumlong onlyshort onlylong short
JAR
2021
J. of Accounting Research
Gow, Larcker & Zakolyukina (2021) *Journal of Accounting Research*: "Non-Answers and Deception in CFO Communication." CFOs whose Q&A answers swing sharply in tone within a single call are more likely defending weak fundamentals.
Citation only — paper link pending.

What it checks

Specifically measures the CFO's tone swings during the analyst Q&A portion. When the CFO oscillates between positive boilerplate and defensive clarifications, expect a forward miss.

Mechanism

When a CFO oscillates between positive boilerplate and negative-tone clarifications during analyst Q&A (high cfo_qa_dispersion in FinBERT scores), they are typically defending weak fundamentals — predicting negative 60-90 day drift independent of the miss/beat itself. The signal isolates *defensive non-answers*: sentence-level CFO tone variance during the Q&A section, z-scored against the firm's own call history.

Signal rule

SHORT when cfo_qa_dispersion own-z >= +1.0 (defensive). LONG when own-z <= -1.0 (consistent / confident).

Data dependencies

  • daily_prices

    Adjusted-close OHLCV for every US-listed ticker; primary price feed.

  • transcript_finbert_scores

    Worker data table — see services/worker schema.

Expected edge

Paper window
2003-2018

Predicts negative 60-90 day drift independent of the print's miss/beat, with effect strongest on guidance-miss quarters.

Illustrative pattern only

NOT a backtest

Illustrative pattern only — see /app for live backtests and the actual current equity curve.

Related families

transcript finbert qa dispersionText-NLP

Huang-Wang-Yang (2023 CAR) "FinBERT: A Large Language Model for Extracting Information from Financial Text." FinBERT-tone outperforms Loughran-McDonald wordcount on every post-call drift measure tested (3-day CAR R² roughly doubles). Follow-up Chen et al. (2024 JFE) reports ~5% annualised L/S on the Q&A-dispersion sub-signal. Own-history z of per-call Q&A sentiment dispersion (stdev of per-sentence pos-neg score): short when z ≥ +1 (uncertainty), long when z ≤ −1 (confident answers).

transcript qa evasionText-NLP

Bochkay-Brown-Leone-Tucker (2024 JAR) "Managers' Use of Language in Earnings Conference Calls and Future Performance." Signal is the semantic distance between an analyst's question and management's answer. When the answer is far from the question (mgmt evading), the firm underperforms over the next 60 days. Reported: LS quintile Sharpe 1.4, 7.8% annualised. v1 uses Jaccard token-overlap distance as a CPU-only proxy; v2 will swap to sentence-embedding cosine.

transcript exec tone divergenceText-NLP

When the CEO and CFO speak with different sentiment tones on the same earnings call, post-earnings drift skews negative. We compute |ceo_tone − cfo_tone| per call from FinBERT scores on speaker-tagged transcript segments, then z-score against the firm's own history. A high absolute divergence implies the strategic narrative (CEO) and financial detail (CFO) are misaligned — a bearish setup. Negative z (unusually aligned tones) acts as a confidence proxy.

Explore transcript cfo qa defensiveness on alphactor.ai

See which tickers this family is currently firing on, with live signals and rankings.

For informational and educational purposes only. Not financial advice. Learn more