Thesis
The mean-reversion strategy operates on one of the oldest principles in quantitative finance: prices tend to revert toward their historical mean after extremes. The rule is deliberately simple — buy when RSI drops below 30 (oversold), sell when RSI climbs above 70 (overbought). The universe spans 24 large-cap U.S. equities across tech, financials, healthcare, consumer staples, and energy, giving the algorithm a diversified hunting ground for temporary dislocations.
Backtest Performance
Over 451 days of simulation, the strategy generated a 14.73% total return on a $10,000 starting portfolio, compounding to a CAGR of roughly 7.98%. The 70.6% win rate across 38 trades is legitimately strong for a rules-based system — most mean-reversion strategies in this asset class settle in the 55–65% range.
The Sharpe ratio of 0.58 is modest but acceptable given the strategy's low trade frequency. Maximum drawdown reached 15.64%, which is within tolerable bounds for a long-only equity approach, though it isn't trivial. Turnover of 879% annualized reflects the rapid entry-and-exit nature of RSI-driven signals rather than a buy-and-hold posture.
Walk-Forward Validation: A Mixed Picture
The 4-fold walk-forward cross-validation is where things get more nuanced — and more honest.
| Fold | Period | Return | Sharpe | Max DD | Trades |
|---|---|---|---|---|---|
| 1 | Aug 2024 – Jan 2025 | +2.06% | 0.57 | 4.24% | 8 |
| 2 | Jan 2025 – Jul 2025 | +11.10% | 1.32 | 10.53% | 10 |
| 3 | Jul 2025 – Dec 2025 | +2.21% | 0.46 | 8.80% | 6 |
| 4 | Dec 2025 – May 2026 | -2.84% | -0.33 | 14.96% | 10 |
Three of four folds were profitable. Fold 2 stands out — an 11.1% return with a Sharpe of 1.32 suggests the strategy found an ideal environment, likely a period of elevated volatility with clear mean-reverting bounces. But Fold 4, the most recent and most forward-looking period, returned -2.84% with a negative Sharpe and the largest intra-fold drawdown of nearly 15%.
The Probabilistic Sharpe Ratio (PSR) of 0.785 indicates there is meaningful statistical uncertainty around whether the observed Sharpe reflects genuine edge or noise. The Deflated Sharpe Ratio (DSR) of 0.304 — which adjusts for the number of trials tested (6) — is low enough to flag real concern about data-mining bias.
The validation gate did not pass.
Live Deployment
Despite the failed validation, the strategy is live with a $10,000 allocation. Its first trade: 21 shares of WMT at $115.75, executed on May 31st, leaving $7,569 in cash. WMT's presence in the consumer staples universe makes it a logical first signal — defensive large-caps tend to show cleaner RSI reversions than high-beta names.
Strengths and Risks
Strengths: High win rate, simple and auditable logic, broad universe diversification, low fee drag ($38 total across 38 trades).
Risks: The most recent fold underperformed, and the DSR suggests the backtest may be partially a product of parameter selection rather than robust edge. Mean-reversion strategies are known to struggle in trending markets — a sustained directional move in any core holding can overwhelm the RSI signal and extend drawdowns well beyond historical norms.
This one warrants close monitoring through its first 30–60 live trading days before drawing conclusions.