Quantitative research · S&P 500 · 2021–2026

Do earnings-day price gaps predict what happens next?

When a stock gaps up or down right after reporting earnings, does that move tend to continue or reverse over the following days and weeks? We tested it rigorously across the entire S&P 500.

Understand earnings risk, test market narratives, and see what actually holds up out of sample — this isn't a stock-prediction tool.

Headline finding

No.

Tested whether earnings-day price gaps predict forward returns across 10,135 events in the S&P 500. After controlling for general market movement, no tradeable edge survives out-of-sample testing. Raw returns looked significant in every bucket — but that turned out to be almost entirely general market movement, not a gap-specific effect. Once that's controlled for, effect sizes collapse by an order of magnitude, and none of what remains held up when tested on data withheld during exploration.

544
Companies
10.1K
Earnings events
10,135
713K
Daily price rows
0/20
Patterns held up out-of-sample

How we tested it

Reaction-day detection

Earnings-date timestamps don't reliably say whether a report was before or after market close, so the actual reaction day was inferred from a volume-spike heuristic, aggregated per company with a confidence score.

Market-adjusted returns

Raw returns were dominated by general market beta. Every result here is measured against the S&P 500's own return over the identical window, isolating whatever is actually gap-specific.

Out-of-sample validation

Patterns were identified on one slice of the data and re-tested, unmodified, against a held-out later period — the check most retail backtests skip.

Transaction costs

A flat 0.1% slippage-and-spread assumption per side is subtracted from every return before re-testing significance, not just the average.