Research › Business Verdicts
Artul.ai Research LibraryStudy No. 92Business VerdictsUpdated 2026-08-28

Guidance Is a Vibe: Calls Where Demand Reads as Accelerating

By Artul.ai Research Group · n = 58,672 earnings calls · First published 2026-08-28
Abstract

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).

Key findings
  • 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%.

Table 1. Mean behavioral scores (0–9 scale), study group versus baseline
MeterStudy groupBaselineΔ
Candor6.796.86-0.07
Evasion2.582.70-0.12
Specificity7.697.56+0.13
Stress1.972.43-0.46
Promotion5.555.05+0.50
Confidence7.767.21+0.55
Table 2. Guidance actions, study group versus baseline
ActionStudy groupBaseline
Raised37.0%21.1%
Maintained45.6%48.8%
Lowered3.1%11.6%
Withdrawn1.3%2.7%
Table 3. Co-occurring battery signals ranked by lift (group prevalence ÷ baseline prevalence)
SignalLiftIn groupBaseline
Volume About to Step Up1.60×45.5%28.5%
Deferred Revenue Growing1.57×13.9%8.9%
Early Products Growing Fast1.47×56.5%38.5%
A Tiny Fraction of the Market1.34×40.4%30.0%
Pricing Recovering1.33×28.6%21.5%
The Hidden Segment0.67×14.1%21.1%
The Finished-Story Tell0.70×3.1%4.4%
Results Worse Than Direction0.71×36.1%51.1%
201520.82%
201626.12%
201737.32%
201837.91%
201929.21%
202034.87%
202162.79%
202236.38%
202327.54%
202432.00%
202526.40%
Figure 1. Share of all analyzed calls matching the study definition, by year.
Table 4. Twelve-month excess total returns versus SPY (descriptive history, not a signal)
StatisticStudy groupReturns sample
Median excess return-4.6%-7.2%
Interquartile range-24.2% to +15.3%
Share beating SPY43.7% (95% CI 43%–45%)39.5%
Observations8,09522,449
Table 5. Most recent calls matching the study definition
TickerQuarterCall dateCall grade
SBFGQ2 20252025-07-25A
USCBQ2 20252025-07-25B+
MOG.AQ3 20252025-07-25B+
AMSFQ2 20252025-07-25C+
LARKQ2 20252025-07-25B
FLGQ2 20252025-07-25B
FRSTQ2 20252025-07-25A
HMDPFQ2 20252025-07-25B

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.

Cite this study Artul.ai Research Group (2026). “Guidance Is a Vibe: Calls Where Demand Reads as Accelerating.” Artul.ai Earnings-Call Research Library, Study No. 92. https://artul.ai/research/when-demand-is-accelerating-earnings-calls

Related studies

Steady As She Goes: What Happens When Guidance HoldsMargins Are Expanding, and So Is the Confidence: ReaCapex Up, Stress Down: Reading 64,183 Calls Where SpBacklog Is Growing, and So Is the Confidence: EarninMargins Are Fine, Thanks for Asking: What ContractioShow Me the Money (Ask): Calls Where Pricing Read as
Not investment advice. Artul.ai publishes AI-generated earnings-call quality grades and expected-volatility estimates — never buy or sell recommendations. We tested over 1,600 predictive hypotheses against 165,000 transcripts; the honest result, including what failed, is documented in our methodology.