Thesis
bollinger-reversion is a textbook mean-reversion play: buy a name when it trades below its lower Bollinger band, sell when it pushes above the upper band. It runs across a 24-stock universe of US large caps — AAPL, MSFT, NVDA, JPM, JNJ, XOM and peers — betting that short-term dislocations in liquid blue chips snap back toward the mean. It's a clean, interpretable idea, and that transparency is a genuine point in its favour.
Recent activity
The scheduled runs tell a quieter story than the thesis. Across the last six sessions (2026-09-25 to 2026-10-02), most runs executed nothing while flagging a single rejected order — a candidate the strategy's checks declined. The 2026-10-02 run was the exception, executing two trades: a 9-share buy of JNJ at $255.36 and a 1-share sell of CAT at $847.03. Other recent executed trades include buying NKE (70 shares at $35.64) and MCD, and selling WMT and GOOGL. Live equity has drifted in a $9,516–$9,734 band — notably below the $10,000 the backtest implies as a starting stake, so the live book is currently underwater even while the backtest shows a gain.
Backtest & validation
On paper the backtest is attractive: +17.55% total return over 451 days, a 9.46% CAGR, a 63.89% win rate across 76 trades, and only $76 in fees. But the Sharpe is a modest 0.66 and the max drawdown a steep 20.57% — this is a strategy that has made you sit through real pain for its returns.
The validation layer is where enthusiasm should cool: it did not pass. All four walk-forward folds were positive, which sounds reassuring, but the trend is unmistakable decay. Fold 1 returned 7.67% at a 1.78 Sharpe, then 1.42%, then 0.77%, and finally just 0.40% at a 0.14 Sharpe in the most recent window (ending 2026-05-29). The out-of-sample Sharpe of 0.14 and OOS return of 0.40% say the edge has thinned to near-zero recently. With a deflated Sharpe ratio of 0.342 across 6 trials, the odds that the headline Sharpe survives a multiple-testing adjustment are low.
Verdict
The strengths are real: a legible thesis, a high win rate, minimal fees, and four consecutive positive folds. The risks are just as real: deteriorating out-of-sample performance, a sub-0.5 deflated Sharpe, a 20%-plus drawdown, and a live account below its starting capital. bollinger-reversion looks like a strategy whose edge was strongest in 2024 and early 2025 and has since compressed. Keep it live on a short leash — but don't size it like the 17.55% headline suggests.