Show Me the Money, Up Front: Earnings Calls Where Deferred Revenue Is Growing
This study examines 14,649 earnings calls (8.87% of a 165,182-call corpus spanning 1990-2026) where the model answered YES to the battery item "Deferred Revenue Growing." Calls in this group show a more promotional and confident tone than the base: promotion scores 5.57 vs. 5.05 and confidence 7.54 vs. 7.21. Guidance behavior also differs, with 33.0% of these calls raising guidance versus 21.1% in the base. Among 2,336 calls with measured post-call outcomes, the median return was -0.46% versus -7.16% for the 22,449-call baseline, and 49.6% beat versus 39.5%. These are descriptive associations, not causal claims or signals.
- Deferred-revenue-growing calls make up 8.87% of the 165,182-call corpus (14,649 calls), with a 95% CI of 8.73% to 9.01%.
- Tone differs from the base: promotion is 5.57 vs. 5.05, confidence 7.54 vs. 7.21, and stress 2.21 vs. 2.43.
- Guidance is raised on 33.0% of these calls versus 21.1% of base calls, and withdrawn on only 1.9% versus 2.7%.
- In the 2,336-call returns sample, the median post-call return is -0.46% versus -7.16% for the baseline, with 49.6% beating versus 39.5%.
1Introduction
Deferred revenue is one of the few line items management can barely spin: cash collected before it can be called revenue. A growing deferred revenue balance suggests customers paying ahead, which is why listeners of earnings calls often treat any mention of it as a quiet vote of confidence. But how do calls where the model flags "Deferred Revenue Growing" actually differ from the rest of the corpus in tone, guidance behavior, and measured outcomes? This study examines 14,649 such calls out of 165,182, comparing their language profile, guidance actions, and post-call return distributions against the full baseline.
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 the model answered YES to the battery item "Deferred Revenue Growing" (n = 14,649; 8.9% of the reference set, 95% Wilson interval 8.7%–9.0%). 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
Calls flagged for growing deferred revenue read differently: promotion is higher (5.57 vs. 5.05) and confidence higher (7.54 vs. 7.21), while stress is lower (2.21 vs. 2.43). Guidance skews positive, with 33.0% raising versus 21.1% in the base and withdrawals at 1.9% versus 2.7%. The most over-associated topics include "Early Products Growing Fast" (lift 1.67) and "Founder-Led Companies" (1.54). The annual trend shows prevalence rising from 7.21% in 2015 to a 2021 peak of 10.69%, easing to 8.78% in 2024. In the 2,336-call returns sample, the median post-call return of -0.46% compares with -7.16% for the 22,449-call baseline, and 49.6% beat versus 39.5%.
| Meter | Study group | Baseline | Δ |
|---|---|---|---|
| Candor | 6.75 | 6.86 | -0.11 |
| Evasion | 2.73 | 2.70 | +0.03 |
| Specificity | 7.62 | 7.56 | +0.06 |
| Stress | 2.21 | 2.43 | -0.22 |
| Promotion | 5.57 | 5.05 | +0.52 |
| Confidence | 7.54 | 7.21 | +0.33 |
| Action | Study group | Baseline |
|---|---|---|
| Raised | 33.0% | 21.1% |
| Maintained | 44.5% | 48.8% |
| Lowered | 9.2% | 11.6% |
| Withdrawn | 1.9% | 2.7% |
| Signal | Lift | In group | Baseline |
|---|---|---|---|
| Early Products Growing Fast | 1.67× | 64.4% | 38.5% |
| Founder-Led Companies | 1.54× | 30.9% | 20.0% |
| A Tiny Fraction of the Market | 1.50× | 45.2% | 30.0% |
| Volume About to Step Up | 1.29× | 36.7% | 28.5% |
| The Finished-Story Tell | 0.68× | 3.0% | 4.4% |
| Statistic | Study group | Returns sample |
|---|---|---|
| Median excess return | -0.5% | -7.2% |
| Interquartile range | -21.5% to +21.5% | — |
| Share beating SPY | 49.6% (95% CI 48%–52%) | 39.5% |
| Observations | 2,336 | 22,449 |
| Ticker | Quarter | Call date | Call grade |
|---|---|---|---|
| MOG.A | Q3 2025 | 2025-07-25 | B+ |
| DBOEY | Q2 2025 | 2025-07-25 | B+ |
| CSBR | Q4 2025 | 2025-07-25 | C+ |
| COUR | Q2 2025 | 2025-07-24 | A |
| DLR | Q2 2025 | 2025-07-24 | B |
| ESRT | Q2 2025 | 2025-07-24 | C+ |
| SKYW | Q2 2025 | 2025-07-24 | B+ |
| BX | Q2 2025 | 2025-07-24 | B |
4Discussion
A careful reader should treat these numbers as descriptions of a subgroup, not promises about any single stock. Calls flagged for growing deferred revenue do co-occur with more confident language, more guidance raises, and a better measured return distribution, but nothing here establishes that deferred revenue growth causes those outcomes, nor that the flag predicts future returns. Company mix, sector, and market era all shift over the 1990-2026 span, and the flagged group is a selective slice. The right takeaway is that this phrase pattern marks a distinctive conversational profile, not a verdict on quality.
5Limitations
The battery items are AI-read and noisy, so misclassification blurs both the flagged group and the baseline. The returns sample covers 2,336 flagged calls against a 22,449-call baseline skewed toward liquid names, so outcome comparisons inherit that selection. Artul's own forward tests falsified directional prediction from these signals, and LLMs partially remember famous stocks' histories, contaminating any backtest. Differences here are associations in historical data and should not be used as a trading edge. See the full methodology, including the C1 pattern’s forward-test failure and the LLM-memorization finding.