The Thesis
The premise is classical and deliberately simple: buy any name in a 24-stock blue-chip universe when its RSI drops below 30, sell when it climbs above 70. No macro overlays, no earnings filters — just the signal. The universe spans technology, financials, healthcare, consumer staples, and energy, covering names liquid enough that execution risk is low.
Backtest Snapshot
Over 451 days the strategy returned 14.73% (7.98% annualised CAGR) on a $10,000 starting stake, closing 38 trades with a 70.59% win rate. That strike rate is genuinely notable — nearly three in four trades closed in the green. The Sharpe of 0.58 and maximum drawdown of 15.64% reflect moderate but real risk. One number that deserves a second look: turnover of 879%. The $38 in recorded fees is minimal, but in live conditions slippage on that many round-trips could quietly erode edge.
Validation: Where It Gets Complicated
The strategy did not pass the platform's automated validation gate, and the walk-forward fold data explains why:
| Fold | Period | Return | Sharpe | Max DD |
|---|---|---|---|---|
| 1 | Aug 2024 – Jan 2025 | +2.06% | 0.57 | –4.24% |
| 2 | Jan – Jul 2025 | +11.10% | 1.32 | –10.53% |
| 3 | Jul – Dec 2025 | +2.21% | 0.46 | –8.80% |
| 4 | Dec 2025 – May 2026 | –2.84% | –0.33 | –14.96% |
Fold 2 is exceptional — a 1.32 Sharpe and 11% return in six months suggests markets offered textbook oscillation. But the trend across folds 3 and 4 is harder to dismiss. The out-of-sample (OOS) Sharpe of –0.33 and OOS return of –2.84% reflect the most recent live-equivalent window, and that is the number risk managers weight most heavily. A Probabilistic Sharpe Ratio of 0.785 is acceptable; a Deflated Sharpe Ratio of 0.304 — which penalises the full-sample Sharpe for the six trials run — signals meaningful uncertainty about whether the in-sample edge is real or a product of search.
Recent Activity
The strategy deployed on 31 May 2026 with $10,000. Its first trade: 21 shares of WMT at $115.75, Walmart being the lone RSI<30 signal at launch. The 1 June scheduled run found no new triggers, leaving the portfolio at $9,967.87 — effectively flat in its opening 24 hours and about 75% in cash.
Strengths and Risks
Strengths
- A 70.6% win rate on liquid large-caps suggests the RSI signal has genuine directional value, not just in-sample luck.
- Three of four folds were profitable; the strategy is not uniformly broken.
- The blue-chip universe keeps fees and spread costs manageable.
Risks
- Failed validation is the headline concern. Fold 4's near-15% drawdown points to regime sensitivity: when markets trend rather than oscillate, RSI can fire early — and keep firing — on the wrong side.
- A DSR of 0.304 on six trials means the evidence base for edge persistence is thin. More out-of-sample data is needed before scaling capital.
- High turnover amplifies execution-quality risk in any slippage or spread-widening environment.
Outlook
Mean-reversion on blue-chip equities is well-grounded theoretically; fold 2 alone demonstrates it can work in the right regime. The open question is whether the recent negative fold reflects a structural shift — momentum and trend-following dominated much of late 2025 and early 2026 — or normal variance. The WMT position gives the first live data point. Until fold 5 (the live period) shows a reversal, cautious position sizing and a drawdown circuit-breaker are the sensible guardrails.