The Thesis
The mean-reversion strategy runs a classic contrarian playbook: buy when RSI drops below 30 (oversold) and sell when it climbs above 70 (overbought). It operates on a 24-name universe of large-cap US equities spanning tech, financials, healthcare, staples, and energy — AAPL, MSFT, NVDA, JPM, JNJ, WMT, XOM and others. It is currently flagged live.
Backtest Performance
On paper, the numbers look inviting. Over a 451-day backtest the strategy returned 14.73%, lifting a notional $10,000 to $11,473, for a 7.98% CAGR. The headline strength is consistency of hit rate: a 70.6% win rate across 38 trades. That said, the risk-adjusted picture is more sober — a Sharpe of 0.58 and a 15.64% max drawdown mean returns came with real volatility. Turnover was heavy at 879%, though fees stayed negligible ($38 total).
Where Validation Breaks Down
This is where enthusiasm should cool. The strategy failed cross-validation. Across four walk-forward folds, three were positive — but the crucial fourth and most recent fold (Dec 2025–May 2026) returned -2.84% with a negative Sharpe of -0.33 and a 14.96% drawdown. Out-of-sample results as a whole came in at -2.84% return and -0.33 Sharpe.
The robustness statistics tell the same story. With six trials in the search, the Deflated Sharpe Ratio sits at just 0.304 — below the threshold you would want to trust a signal that survived multiple attempts. A PSR of 0.785 is respectable in isolation, but the DSR deflation and the decaying fold sequence (Sharpe of 1.32 in fold 2 collapsing to -0.33 in fold 4) suggest the edge is fading rather than stable.
Recent Live Activity
Live behaviour reinforces the caution. The last executed trade was a 21-share WMT buy at $115.75 on 31 May 2026 — over three months ago. Every scheduled run since (26 Aug through 2 Sep) reports 0 executed, 0 rejected: no name in the universe has hit the RSI extremes needed to trigger action. Meanwhile the paper portfolio sits at roughly $9,800 total against a $10,000 start, holding $7,569 in cash. In other words, the strategy is currently idle and modestly underwater in live paper trading.
The Balanced Verdict
Strengths: a genuinely high win rate, a coherent and well-understood thesis, and low trading costs. Mean-reversion is a real, documented market behaviour, and a 70% hit rate is not noise.
Risks: the strategy fails validation on exactly the axis that matters — recent, out-of-sample performance. A high win rate paired with a negative most-recent fold hints that the occasional loss is large enough to erase many small wins, and the DSR warns the backtest may be flattered by trial selection. The long stretch with zero trades also raises a practical question: in calm, trending markets, RSI extremes simply may not appear often enough to matter.
The honest read: an interesting, interpretable strategy with a promising in-sample record, but not one to trust with conviction until it proves it can survive out-of-sample. For now, watch — don't lean on it.