The thesis
Mean-reversion is one of the oldest ideas in systematic trading, and this strategy runs the textbook version of it: buy when a name is oversold (RSI below 30) and sell when it is overbought (RSI above 70). It trades a 24-stock large-cap universe — the usual megacap tech, financials, healthcare, and staples names like AAPL, NVDA, JPM, JNJ, and WMT. The bet is simple: short-term price extremes in liquid blue chips tend to snap back.
Recent activity
The strategy is live. It spent late October putting cash to work — buying BAC (48 shares at $51.15), GOOGL (8 at $280.28) and CAT (4 at $622.54) on Oct 29–30, then adding NVDA (13 at $188.24) on Nov 6. Those purchases left it essentially fully invested, with only $271.67 in cash.
Since then it has gone quiet. Every scheduled run from Nov 9 through Nov 13 reported 0 executed, 0 rejected — unsurprising for a fully-deployed book with no names yet hitting the overbought exit. Over that stretch total equity drifted between roughly $9,510 and $9,768, closing the latest run at $9,585.39. In other words, the live account is currently sitting below its starting stake while it waits for the mean-reversion to pay off.
Backtest and validation
On paper the record is attractive. Across 451 days the backtest returned 14.73% (final equity $11,473.17, a 7.98% CAGR), with a 70.59% win rate over 38 trades and a max drawdown of 15.64%. Fees were negligible ($38, no FX cost). The Sharpe, however, is a modest 0.58 — the hit rate is high but the risk-adjusted payoff is ordinary, and turnover is heavy at 879%.
The more important number is that validation failed. Walk-forward testing split the history into four folds; three were positive (+2.06%, +11.10%, +2.21%), but the most recent and most relevant fold — Dec 2025 to May 2026 — lost 2.84% with a negative Sharpe of −0.33 and a 14.96% drawdown. The out-of-sample Sharpe is negative, the deflated Sharpe ratio sits at just 0.30 across 6 trials, and the probabilistic Sharpe is 0.785. The headline return leans heavily on fold 2's strong run.
Strengths and risks
Strengths: a genuinely high win rate, a transparent and well-understood thesis, low trading costs, and a drawdown that stayed contained in three of four folds.
Risks: the strategy did not clear its own validation gate, and the failure is concentrated in the newest data — exactly where you'd want confidence before committing capital. The soft Sharpe and high turnover suggest returns are fragile and churn-heavy, and the live book is already underwater. Mean-reversion also carries its classic tail risk: in a sustained drawdown, "oversold" keeps getting more oversold. This one earns its live slot on paper, but the out-of-sample data argues for watching it closely rather than scaling it up.