Does buying a deeply oversold, high-volatility stock the next day pay by the close? A backtest
A backtest of buying a deeply oversold, volatile stock at the next open: the question, the bar written first, the verdict and its limits. Coil Edge Research.
Hypothetical results from a simulation on historical market data; no money was traded; costs and slippage as assumed in the Method; past and simulated results don't predict future results. Not investment advice.
The question. When a liquid US stock closes a session with high volatility, a low daily RSI and a price well under its medium-term moving average, does buying it at 10:00 ET the next session and selling at the close do better than the S&P 500 over the same hours, after costs? It also asks about random liquid stocks and equally volatile stocks that are not oversold.
The verdict. Not enough evidence either way. The rule did not pass its pre-registered bar. Against the S&P 500 and after costs its average trade was slightly below zero, and neither that nor its small gap over random stocks could be told from zero. A large effect is excluded; a small one is neither confirmed nor ruled out.
Backtest (hypothetical), run in Backtrader 1.9.78.123, data to 2026-10-02
Method, in one paragraph. 10 years of 30-minute bars (2016 to 2026-10-02) for 441 US stocks and SPY. 2,090 hypothetical one-day trades (up to 3 flagged stocks a session, drawn at random), each net of assumed costs and compared with the S&P 500 over the same hours, with random liquid stocks and with equally volatile stocks that are not oversold.
What this does not show.
- The test could see an effect the size of its bar but not a small one; a small effect is neither confirmed nor ruled out.
- About three quarters of flagged stock-days had 30-minute bars, and the uncovered names did worse, so the levels here are tilted up.
- The stock list is today's applied back in time, and 2020 is 46% of the flagged stock-days.
- A simulation is not a record of trades.
The full result tables, the control comparisons and the test statistics are in the paid text. A person pays from a crypto wallet (USDC on Base); an AI agent pays over x402. There is no card option for a single study.
Buy the full study ($0.25, pay with a crypto wallet)
Does buying a deeply oversold, high-volatility stock the next day pay by the close?
Not enough evidence either way. The rule did not pass its pre-registered bar; its average trade was slightly below zero against the S&P 500 after costs, and a small effect can be neither confirmed nor ruled out.
Coil Edge Research, 2026-10-22.