Attention Spike
In plain terms
When Google searches for a ticker spike abnormally, retail piles in and overpays. Short-term the price runs, then mean-reverts.
How it works
Da-Engelberg-Gao 2011 "In Search of Attention": abnormal Google search volume (SVI z-score over a trailing 52-week baseline) predicts short-run overpricing — when SVI z > +2 retail piles in and the price mean-reverts over 2-4 weeks. Especially strong in retail-heavy names (small/mid-cap, meme stocks). Trends is weekly; we forward-fill onto the daily price index and use the harness's random-shuffle test to gate the small per-name edge.
Live results
7 times picked on its own · 28 times inside a blend (22 beat the stock) · updated 2026-06-06Data dependencies
- Google trends svi
Google search-volume index for the ticker as keyword.
Expected edge
- Reported return
- ~3% on 2-week long; 6-month short basket
- Tested over
- 2004-2008 (Da-Engelberg-Gao)
2-week long for spike, 6-month short basket for unwinding (Da-Engelberg-Gao 2011)
Example tickers where this is likely to fire
Illustrative only, the signal fires based on the live data, not a fixed list.
Related families
Abnormal Wikipedia pageviews for a ticker predict a 2-week rally then a year-out reversal. Cleaner than Google Trends per Pyun 2024.
Listens to how steady management's tone is during analyst Q&A. If answers swing between confident and defensive, it usually signals trouble ahead.
Explore Attention Spike on alphactor.ai
See which tickers this family is currently firing on, with live signals and rankings.