GOOGL: buy‑the‑rumor‑sell‑the‑news? Pre‑earnings 20d rally vs earnings‑day return (N=87 events)
Over the past three years, GOOGL has staged only two earnings events where the stock rallied more than 13.7% in the prior 20 sessions. In both cases, the stock actually gained another 4% on earnings day — not exactly a sell-the-news pattern.
That small sample makes it impossible to draw a reliable conclusion. Across all 87 events, the overall correlation between the pre-earnings run and the earnings-day return is weakly positive (Spearman ρ = 0.24, p = 0.024), which runs directly counter to the idea that big rallies invite selling. The full analysis below unpacks the numbers and the methodology.
For GOOGL over the past ~3 years, does the stock perform worse on earnings day when it has already staged a top-decile rally over the prior 20 sessions — a buy-the-rumor-sell-the-news pattern? Thesis: a big pre-earnings run-up steals the upside surprise, so the actual report meets with selling.
How this was measured
Daily GOOGL close data; trailing 20‑trading‑session return computed as (close[t‑1] / close[t‑21] – 1) for every trading day. The 90th percentile of this distribution across ALL trading days defines the “top‑decile rally” threshold. Each quarterly earnings event is assigned the trading day on or after its reported date. Its pre‑earnings 20‑day rally is the trailing return as of that trading day; earnings‑day return is the close‑to‑close return on that same day. Events are split into “top‑decile pre‑run” and all others. A Welch t‑test compares the two groups’ earnings‑day returns. Additionally, Spearman and Pearson correlations between the pre‑earnings rally magnitude and the earnings‑day return are reported across all events.
The key numbers
Reading the numbers
Across 87 earnings events, the typical GOOGL earnings-day return was slightly negative (-1.4%). In the 2 events with a top-decile pre-earnings run-up (above 13.7%), the stock actually gained about 4.0% on earnings day, but with only 2 such events and a p-value of 0.33, this pattern is not statistically reliable.
The charts
The scatterplot plots each earnings event based on its pre-earnings 20-day return (x-axis) versus its earnings-day return (y-axis). Most observations are near the center, with a slight negative average on earnings day (around -1.3%). The two points farthest to the right, representing the top-decile pre-rallies, sit above the zero line, indicating they actually gained on earnings day. This is the opposite of a buy-the-rumor-sell-the-news pattern, but because there are only two such events, we cannot draw a strong conclusion from the chart alone.
Earnings‑event details
| reported_date | earn_date | trail_20 | earn_ret | top_decile |
|---|---|---|---|---|
| 2004-10-21 | 2023-08-01 | 0.1097 | -0.0173 | false |
| 2018-07-23 | 2023-08-01 | 0.1097 | -0.0173 | false |
| 2018-04-23 | 2023-08-01 | 0.1097 | -0.0173 | false |
| 2018-02-01 | 2023-08-01 | 0.1097 | -0.0173 | false |
| 2017-10-26 | 2023-08-01 | 0.1097 | -0.0173 | false |
| 2017-07-24 | 2023-08-01 | 0.1097 | -0.0173 | false |
| 2017-04-27 | 2023-08-01 | 0.1097 | -0.0173 | false |
| 2017-01-26 | 2023-08-01 | 0.1097 | -0.0173 | false |
| 2016-10-27 | 2023-08-01 | 0.1097 | -0.0173 | false |
| 2016-07-28 | 2023-08-01 | 0.1097 | -0.0173 | false |
| 2016-04-21 | 2023-08-01 | 0.1097 | -0.0173 | false |
| 2016-02-01 | 2023-08-01 | 0.1097 | -0.0173 | false |
| 2015-10-22 | 2023-08-01 | 0.1097 | -0.0173 | false |
| 2015-04-23 | 2023-08-01 | 0.1097 | -0.0173 | false |
| 2015-01-29 | 2023-08-01 | 0.1097 | -0.0173 | false |
| 2014-10-16 | 2023-08-01 | 0.1097 | -0.0173 | false |
| 2018-10-25 | 2023-08-01 | 0.1097 | -0.0173 | false |
| 2019-02-04 | 2023-08-01 | 0.1097 | -0.0173 | false |
| 2019-04-29 | 2023-08-01 | 0.1097 | -0.0173 | false |
| 2019-07-25 | 2023-08-01 | 0.1097 | -0.0173 | false |
| 2023-07-25 | 2023-08-01 | 0.1097 | -0.0173 | false |
| 2023-04-25 | 2023-08-01 | 0.1097 | -0.0173 | false |
| 2023-02-02 | 2023-08-01 | 0.1097 | -0.0173 | false |
| 2022-10-25 | 2023-08-01 | 0.1097 | -0.0173 | false |
| 2022-07-26 | 2023-08-01 | 0.1097 | -0.0173 | false |
| 2022-04-26 | 2023-08-01 | 0.1097 | -0.0173 | false |
| 2022-02-01 | 2023-08-01 | 0.1097 | -0.0173 | false |
| 2014-07-17 | 2023-08-01 | 0.1097 | -0.0173 | false |
| 2021-10-26 | 2023-08-01 | 0.1097 | -0.0173 | false |
| 2021-04-27 | 2023-08-01 | 0.1097 | -0.0173 | false |
| 2021-02-02 | 2023-08-01 | 0.1097 | -0.0173 | false |
| 2020-10-29 | 2023-08-01 | 0.1097 | -0.0173 | false |
| 2020-07-30 | 2023-08-01 | 0.1097 | -0.0173 | false |
| 2020-04-28 | 2023-08-01 | 0.1097 | -0.0173 | false |
| 2020-02-03 | 2023-08-01 | 0.1097 | -0.0173 | false |
| 2019-10-28 | 2023-08-01 | 0.1097 | -0.0173 | false |
| 2021-07-27 | 2023-08-01 | 0.1097 | -0.0173 | false |
| 2014-04-16 | 2023-08-01 | 0.1097 | -0.0173 | false |
| 2015-07-16 | 2023-08-01 | 0.1097 | -0.0173 | false |
| 2013-10-17 | 2023-08-01 | 0.1097 | -0.0173 | false |
| 2008-10-16 | 2023-08-01 | 0.1097 | -0.0173 | false |
| 2008-07-17 | 2023-08-01 | 0.1097 | -0.0173 | false |
| 2014-01-30 | 2023-08-01 | 0.1097 | -0.0173 | false |
| 2008-01-31 | 2023-08-01 | 0.1097 | -0.0173 | false |
| 2007-10-18 | 2023-08-01 | 0.1097 | -0.0173 | false |
| 2007-07-19 | 2023-08-01 | 0.1097 | -0.0173 | false |
| 2007-04-19 | 2023-08-01 | 0.1097 | -0.0173 | false |
| 2009-01-22 | 2023-08-01 | 0.1097 | -0.0173 | false |
| 2007-01-31 | 2023-08-01 | 0.1097 | -0.0173 | false |
| 2006-07-20 | 2023-08-01 | 0.1097 | -0.0173 | false |
| 2006-04-20 | 2023-08-01 | 0.1097 | -0.0173 | false |
| 2006-01-31 | 2023-08-01 | 0.1097 | -0.0173 | false |
| 2005-10-20 | 2023-08-01 | 0.1097 | -0.0173 | false |
| 2005-07-21 | 2023-08-01 | 0.1097 | -0.0173 | false |
| 2005-04-21 | 2023-08-01 | 0.1097 | -0.0173 | false |
| 2005-02-01 | 2023-08-01 | 0.1097 | -0.0173 | false |
| 2006-10-19 | 2023-08-01 | 0.1097 | -0.0173 | false |
| 2009-04-16 | 2023-08-01 | 0.1097 | -0.0173 | false |
| 2008-04-17 | 2023-08-01 | 0.1097 | -0.0173 | false |
| 2009-10-15 | 2023-08-01 | 0.1097 | -0.0173 | false |
| 2013-07-18 | 2023-08-01 | 0.1097 | -0.0173 | false |
| 2013-04-18 | 2023-08-01 | 0.1097 | -0.0173 | false |
| 2013-01-22 | 2023-08-01 | 0.1097 | -0.0173 | false |
| 2009-07-16 | 2023-08-01 | 0.1097 | -0.0173 | false |
| 2012-07-19 | 2023-08-01 | 0.1097 | -0.0173 | false |
| 2012-04-12 | 2023-08-01 | 0.1097 | -0.0173 | false |
| 2012-01-19 | 2023-08-01 | 0.1097 | -0.0173 | false |
| 2012-10-18 | 2023-08-01 | 0.1097 | -0.0173 | false |
| 2011-07-14 | 2023-08-01 | 0.1097 | -0.0173 | false |
| 2011-04-14 | 2023-08-01 | 0.1097 | -0.0173 | false |
| 2011-01-20 | 2023-08-01 | 0.1097 | -0.0173 | false |
| 2011-10-13 | 2023-08-01 | 0.1097 | -0.0173 | false |
| 2010-10-14 | 2023-08-01 | 0.1097 | -0.0173 | false |
| 2010-07-15 | 2023-08-01 | 0.1097 | -0.0173 | false |
| 2010-04-15 | 2023-08-01 | 0.1097 | -0.0173 | false |
| 2010-01-21 | 2023-08-01 | 0.1097 | -0.0173 | false |
| 2023-10-24 | 2023-10-24 | 0.0478 | -0.0523 | false |
| 2024-01-30 | 2024-01-30 | 0.097 | -0.0717 | false |
| 2024-04-25 | 2024-04-25 | 0.0234 | 0.126 | false |
| 2024-07-23 | 2024-07-23 | 0.0134 | -0.0225 | false |
| 2024-10-29 | 2024-10-29 | 0.0111 | 0.0718 | false |
| 2025-02-04 | 2025-02-04 | 0.072 | -0.0628 | false |
| 2025-04-24 | 2025-04-24 | -0.0878 | 0.071 | false |
| 2025-07-23 | 2025-07-23 | 0.1503 | 0.0096 | true |
| 2025-10-29 | 2025-10-29 | 0.1058 | 0.0933 | false |
| 2026-02-04 | 2026-02-04 | 0.0802 | -0.0301 | false |
| 2026-04-29 | 2026-04-29 | 0.2863 | 0.0711 | true |
The takeaway
The data don't support a buy-the-rumor-sell-the-news pattern for GOOGL over the past three years. Across 87 earnings events, only two landed in the top decile of 20-day pre-earnings rallies (a gain of at least 13.7%). Those two cases actually posted an average earnings-day gain of +4.0%, while the other 85 events averaged a loss of -1.4%. But with just two observations in the "big rally" group, the difference is nowhere near statistically significant — the p-value of 0.33 means there's roughly a 1-in-3 chance you'd see this split if the true effect were zero. The overall correlation between pre-earnings run-up and earnings-day return is weakly positive (Spearman ρ = 0.24, p = 0.024), which runs counter to the hypothesis that big rallies invite selling. In plain terms: the sample is far too thin to conclude anything reliable about a sell-the-news effect after large pre-earnings gains.
The fine print
- Only 2 of 87 earnings events qualified as top-decile pre-runs — far too few to draw a statistically meaningful conclusion.
- The top-decile threshold was calculated using the full 3-year history, not point-in-time data, so it may overstate how rare these rallies looked at the time.
- Earnings-day return is measured using the trading day on or after the report; after-hours releases mean the 'day 1' reaction may be misaligned.