Strategy Thesis
The mean-reversion agent operates on one of the oldest premises in quantitative equity trading: prices overshoot in both directions, and rubber-band back. Concretely, the strategy buys any name in its 24-stock large-cap universe when RSI drops below 30 (oversold) and exits when RSI crosses above 70 (overbought). The universe spans technology, financials, healthcare, consumer staples, and energy — a deliberate cross-sector spread designed to keep opportunity flow steady regardless of which pocket of the market is stressed at any given time.
Backtest Headline Numbers
Over the 451-day backtest window, the strategy executed 38 round-trip trades and produced a 14.73% total return (7.98% CAGR), with a 70.59% win rate — meaning roughly seven out of every ten trades were closed profitably. The Sharpe ratio of 0.58 is modest but positive, and total fees came in at a flat $38 (one dollar per trade), keeping friction negligible.
The shadow in the headline is a 15.64% maximum drawdown. For a strategy trading blue-chip names with high cash reserves, that's a meaningful peak-to-trough. Annualised turnover clocks at 879%, which is high for a signal that should fire infrequently — worth watching as the live universe grows.
Walk-Forward Validation: Where the Cracks Show
The strategy did not pass Headmars' automated validation gate, and the walk-forward breakdown explains why.
| Fold | Period | Return | Sharpe | Max DD | Trades |
|---|---|---|---|---|---|
| 1 | Aug 2024 – Jan 2025 | +2.06% | 0.57 | 4.24% | 8 |
| 2 | Jan – Jul 2025 | +11.10% | 1.32 | 10.53% | 10 |
| 3 | Jul – 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, but the trend is discouraging: the edge peaked sharply in fold 2 (Sharpe 1.32) and has eroded each period since. The out-of-sample (most-recent-fold) return of −2.84% and Sharpe of −0.33 represent the live regime the strategy is currently operating in.
The Probabilistic Sharpe Ratio sits at 0.785 — a reasonable but not decisive signal that the historical Sharpe exceeds zero. The Deflated Sharpe Ratio of 0.304 is the sharper concern: once corrected for the number of trials (six parameter sets tested), the probability that the edge is real rather than mined drops meaningfully. This is the primary reason validation failed.
Recent Live Activity
The strategy's last executed trade was a 21-share buy of WMT at $115.75 on 31 May 2026. Since then, six consecutive daily runs through 29 June have produced zero executions — the RSI thresholds simply haven't been met across the 24-stock universe. The portfolio holds $7,569 in cash against a total value of roughly $9,974–$10,084 (mark-to-market has drifted modestly with the WMT position).
The inactivity is a double-edged signal. On one hand, the strategy is behaving exactly as designed — it waits for genuine extremes rather than forcing trades. On the other, in a trending or range-bound bull market where large-caps rarely dip to RSI 30, the strategy may go long stretches generating no alpha.
Balanced Assessment
Strengths: High historical win rate, defined entry/exit rules, low fee drag, meaningful upside in volatile regimes (fold 2 shows the ceiling).
Risks: Validated edge is statistically fragile (DSR 0.30); most recent out-of-sample period is the strategy's worst; high turnover relative to expected signal frequency suggests the RSI thresholds may need recalibration; the strategy is effectively cash-heavy and idle in current market conditions.
The mean-reversion agent is a disciplined rules follower in need of a regime audit. A tighter DSR and at least one more positive OOS fold would be needed before this strategy earns a green validation badge.