Guidance Is a Vibe: Calls Where Demand Reads as Accelerating
This study examines 58,672 earnings calls—35.5% of a 165,182-call corpus spanning 1990 to 2026—where demand was read as accelerating. These calls show a distinct behavioral profile: confidence runs 7.76 versus a 7.21 baseline, promotion language 5.55 versus 5.05, and stress 1.97 versus 2.43. Management behavior diverges too: 36.99% raised guidance against 21.05% of baseline calls, while only 3.07% lowered it versus 11.56%. In the 8,095-call subset with outcome data, 43.67% of these calls beat expectations versus 39.47% of 22,449 baseline calls, with a median return of -4.64% versus -7.16%. The most over-indexed language themes include 'Volume About to Step Up' (1.6x) and 'Deferred Revenue Growing' (1.57x).
- Calls read as demand-accelerating account for 35.5% of the corpus (58,672 of 165,182 calls, CI 35.3%-35.8%).
- Guidance behavior differs sharply: 36.99% raised guidance versus 21.05% of baseline calls, and 3.07% lowered versus 11.56%.
- Behavioral deltas are notable: confidence +0.55, promotion +0.50, and stress -0.46 versus baseline.
- In the returns sample, 43.67% beat expectations versus 39.47% baseline, and median returns were -4.64% versus -7.16%.
1Introduction
Earnings calls are full of demand talk, but 'demand is accelerating' is a phrase managers reach for at emotionally loaded moments—sometimes near peaks, sometimes at inflections. Whether that language marks genuine momentum or simply heightened enthusiasm is worth measuring rather than assuming. We use Artul.ai's behavioral read of 165,182 calls from 1990 through 2026, of which 58,672 (35.5%) were classified as showing accelerating demand. This study profiles those calls: their language themes, guidance actions, behavioral markers, prevalence over time, and post-call outcomes.
2Data & methodology
The corpus comprises 165,182 earnings-call transcripts published between 1990 and 2026, each scored independently by a large language model on an identical 37-field battery: seven categorical business verdicts, eight 0–9 behavioral meters, and twenty yes/no judgments. The study group is defined as calls where demand was read as accelerating (n = 58,672; 35.5% of the reference set, 95% Wilson interval 35.3%–35.8%). Baseline figures use all scored calls. Market outcomes join a fixed sample of 22,449 calls with twelve-month total returns in excess of SPY, measured from the first close after each call; this sample skews toward liquid U.S. names and is reported as descriptive history only.
3Results
The behavioral profile stands out: confidence is 7.76 versus 7.21 and promotion 5.55 versus 5.05, while stress is lower at 1.97 versus 2.43—managers sound calmer and more promotional. Guidance skew is strong, with raises at 36.99% versus 21.05% and lowers at just 3.07% versus 11.56%. Language themes over-index on volume and backlog signals ('Volume About to Step Up' at 1.6x, 'Deferred Revenue Growing' at 1.57x) and under-index finished-story and hidden-segment talk (0.7x and 0.67x). Prevalence peaked at 62.79% of calls in 2021 before falling to 26.4% in 2025. Outcomes skew modestly favorable: 43.67% beats versus 39.47% baseline and median returns of -4.64% versus -7.16%.
| Meter | Study group | Baseline | Δ |
|---|---|---|---|
| Candor | 6.79 | 6.86 | -0.07 |
| Evasion | 2.58 | 2.70 | -0.12 |
| Specificity | 7.69 | 7.56 | +0.13 |
| Stress | 1.97 | 2.43 | -0.46 |
| Promotion | 5.55 | 5.05 | +0.50 |
| Confidence | 7.76 | 7.21 | +0.55 |
| Action | Study group | Baseline |
|---|---|---|
| Raised | 37.0% | 21.1% |
| Maintained | 45.6% | 48.8% |
| Lowered | 3.1% | 11.6% |
| Withdrawn | 1.3% | 2.7% |
| Signal | Lift | In group | Baseline |
|---|---|---|---|
| Volume About to Step Up | 1.60× | 45.5% | 28.5% |
| Deferred Revenue Growing | 1.57× | 13.9% | 8.9% |
| Early Products Growing Fast | 1.47× | 56.5% | 38.5% |
| A Tiny Fraction of the Market | 1.34× | 40.4% | 30.0% |
| Pricing Recovering | 1.33× | 28.6% | 21.5% |
| The Hidden Segment | 0.67× | 14.1% | 21.1% |
| The Finished-Story Tell | 0.70× | 3.1% | 4.4% |
| Results Worse Than Direction | 0.71× | 36.1% | 51.1% |
| Statistic | Study group | Returns sample |
|---|---|---|
| Median excess return | -4.6% | -7.2% |
| Interquartile range | -24.2% to +15.3% | — |
| Share beating SPY | 43.7% (95% CI 43%–45%) | 39.5% |
| Observations | 8,095 | 22,449 |
| Ticker | Quarter | Call date | Call grade |
|---|---|---|---|
| SBFG | Q2 2025 | 2025-07-25 | A |
| USCB | Q2 2025 | 2025-07-25 | B+ |
| MOG.A | Q3 2025 | 2025-07-25 | B+ |
| AMSF | Q2 2025 | 2025-07-25 | C+ |
| LARK | Q2 2025 | 2025-07-25 | B |
| FLG | Q2 2025 | 2025-07-25 | B |
| FRST | Q2 2025 | 2025-07-25 | A |
| HMDPF | Q2 2025 | 2025-07-25 | B |
4Discussion
A careful reader should conclude that calls read as demand-accelerating coincide with more confident delivery, more guidance raises, and slightly better subsequent outcomes than baseline. That is a description of co-occurrence, not a cause or a signal. The beat-rate gap of roughly four points is real in this sample but modest, and median returns remain negative for both groups. The 2021 peak and subsequent fade also show how sentiment-speak clusters with market cycles. Nothing here predicts which calls will outperform; it characterizes how this language behaves.
5Limitations
All fields are AI-read and noisy, so classification errors blur group boundaries. The returns sample covers 8,095 calls with a 22,449-call baseline, skewed toward liquid names, so outcomes may not generalize. Our own forward tests falsified directional prediction—these statistics describe the sample, not an edge. Finally, LLMs partially remember famous stocks' histories, which can contaminate any backtest by leaking hindsight into the behavioral reads themselves. See the full methodology, including the C1 pattern’s forward-test failure and the LLM-memorization finding.