Accentuate the Positive: Earnings Calls That Talk Up Possibilities
This study examines 130 earnings calls (out of a 371-call corpus spanning 2015 to 2024) where the research hypothesis held: Q&A flipped from problems to possibilities and management answered accordingly. These calls show higher confidence (7.77 vs 7.29), stronger promotion framing (5.61 vs 5.01), and lower stress (1.91 vs 2.49) than the baseline. Guidance was raised on 33.1% of these calls versus 22.1% in the base. Themes most overrepresented include 'Early Products Growing Fast' (1.52x lift) and 'A Tiny Fraction of the Market' (1.47x). The share of calls peaked at 0.15 in 2021 and fell to 0.06 by 2024. Among 41 calls with forward returns, the median was -13.0%.
- The pattern appears in 130 of 371 calls (35.0%), with a 95% confidence interval of 30.4% to 40.0%.
- Management confidence scores run 7.77 versus a 7.29 baseline, and stress scores 1.91 versus 2.49.
- Guidance was raised on 33.1% of matching calls versus 22.1% of the base, and lowered on only 3.1% versus 12.7%.
- Among the 41 calls with forward return data, the median return was -13.0% versus -6.0% for the base sample.
1Introduction
Anyone who listens to earnings calls knows the moment when the Q&A turns: analysts stop probing problems and start asking about possibilities, and management leans in. That shift is a recognizable texture of the genre, but it has rarely been measured at scale. Because these calls coincide with noticeably more confident tone and more frequent guidance raises, they are a natural lens on how optimism is expressed in public markets. This study examines 130 calls from a 371-call corpus spanning 2015 through 2024 that matched the hypothesis, comparing their tone profiles, guidance behavior, recurring themes, and forward return outcomes against the rest of the corpus.
2Data & methodology
The corpus comprises 371 earnings-call transcripts published between 2015 and 2024, 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 that answered YES to the research hypothesis "Q&A has flipped from problems to possibilities, and management answers with the " (n = 130; 35.0% of the reference set, 95% Wilson interval 30.4%–40.0%). Baseline figures use the set of calls on which this question was tested. 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 matching the pattern show clear tone differences: confidence is higher (7.77 vs 7.29), promotion framing stronger (5.61 vs 5.01), and stress lower (1.91 vs 2.49), while candor, evasion, and specificity barely move. Guidance behavior skews positive: raised on 33.1% of matching calls versus 22.1% of the base, and lowered on just 3.1% versus 12.7%. Thematically, 'Early Products Growing Fast' carries a 1.52x lift and 'A Tiny Fraction of the Market' 1.47x, while 'When the CFO Dominates' appears at only 0.56x. The annual share of such calls peaked at 0.15 in 2021 and declined to 0.06 by 2024. Notably, the median forward return on 41 matching calls was -13.0%, below the -6.0% base median.
| Meter | Study group | Baseline | Δ |
|---|---|---|---|
| Candor | 6.75 | 6.92 | -0.17 |
| Evasion | 2.79 | 2.76 | +0.03 |
| Specificity | 7.62 | 7.63 | -0.01 |
| Stress | 1.91 | 2.49 | -0.58 |
| Promotion | 5.61 | 5.01 | +0.60 |
| Confidence | 7.77 | 7.29 | +0.48 |
| Action | Study group | Baseline |
|---|---|---|
| Raised | 33.1% | 22.1% |
| Maintained | 53.1% | 53.1% |
| Lowered | 3.1% | 12.7% |
| Withdrawn | 0.8% | 1.1% |
| Signal | Lift | In group | Baseline |
|---|---|---|---|
| Early Products Growing Fast | 1.52× | 56.2% | 36.9% |
| A Tiny Fraction of the Market | 1.47× | 42.3% | 28.8% |
| Founder-Led Companies | 1.47× | 29.2% | 19.9% |
| Volume About to Step Up | 1.27× | 31.5% | 24.8% |
| When the CFO Dominates | 0.56× | 8.5% | 15.1% |
| Results Worse Than Direction | 0.61× | 28.5% | 46.4% |
| The Hidden Segment | 0.71× | 16.9% | 24.0% |
| Statistic | Study group | Returns sample |
|---|---|---|
| Median excess return | -13.0% | -6.0% |
| Interquartile range | -37.8% to +9.6% | — |
| Share beating SPY | 43.9% (95% CI 30%–59%) | 42.1% |
| Observations | 41 | 145 |
| Ticker | Quarter | Call date | Call grade |
|---|---|---|---|
| CRGO | Q1 2024 | 2024-05-20 | C+ |
| ERO | Q1 2024 | 2024-05-10 | A |
| WRBY | Q1 2024 | 2024-05-09 | A |
| HCKT | Q1 2024 | 2024-05-08 | C |
| CW | Q1 2024 | 2024-05-02 | B+ |
| TTI | Q1 2024 | 2024-05-01 | A |
| WEC | Q1 2024 | 2024-05-01 | A |
| LTRX | Q3 2024 | 2024-04-29 | C |
4Discussion
A careful reader should conclude that calls matching this optimistic Q&A pattern sound different: more confident, more promotional, less stressed, and more likely to accompany raised guidance. The theme lifts show which narratives co-occur, with growth stories like 'Early Products Growing Fast' at 1.52x and cautionary structures like 'When the CFO Dominates' at 0.56x. What should not be concluded is that the pattern predicts anything. The forward return data go the other way descriptively, with a median of -13.0% versus -6.0% in the base, but this is an observational association, not a forecast, and the sample is small.
5Limitations
The tone scores and theme labels come from AI-read fields and are inherently noisy, so individual call classifications should be treated as approximate. The returns comparison covers only 41 matching calls and 145 base calls, drawn from a broader returns universe of 22,449 calls skewed toward liquid names, so medians may not generalize. Our own forward tests on similar features falsified directional prediction, and LLMs partially remember famous stocks' histories, contaminating any backtest. No causal claim is supported by these statistics. See the full methodology, including the C1 pattern’s forward-test failure and the LLM-memorization finding.
Companion page: every company matching this hypothesis is listed at the question’s own page.