The thesis
momentum-code runs one of the oldest ideas in systematic trading: buy the strongest recent movers and let winners run, with a per-position cap to stop any single name from dominating. It fishes in a 24-stock pond of US large caps — the usual megacap tech (AAPL, MSFT, NVDA), financials (JPM, V, MA), staples (PG, KO, WMT) and a few cyclicals (XOM, CAT, HD). It is simple, transparent, and easy to reason about, which is exactly what you want from a strategy you intend to trust with live capital.
Recent activity
The strategy opened its current book on 29–30 October, buying into MA, HD, NKE, XOM and WMT. Those entries drew cash down from $4,063 to just $177.08 — essentially fully invested. Since then the story is almost entirely rejections: runs on 2, 3, 4 and 5 November each executed zero trades while rejecting one or two candidates. With only $177 in cash, the engine simply can't fund the next momentum signal. The portfolio has drifted around the $9,876–$10,186 range, closing the latest run at $10,057.82 — roughly flat on its ~$10k base.
This is a real operational risk, not a cosmetic one: a momentum book that can't rotate is no longer a momentum book. It's a static basket of whatever last week's leaders were.
Backtest and validation
On paper the history looks good. Over 451 days the backtest returned 19.76% (10.6% CAGR) to a final equity of $11,976, on just five trades and a trivial $5 in fees. More encouraging, all four walk-forward folds were positive — 15.38%, 3.27%, 12.18% and 13.71% — with out-of-sample Sharpe ratios as high as 2.47. Consistency across time is the hardest thing to fake, and this strategy has it.
And yet the validation gate reads passed: false. The reason is in the deflated statistics. The Probabilistic Sharpe Ratio is a healthy 0.811, but the Deflated Sharpe Ratio is only 0.338 — once you penalise the full-period Sharpe of 0.65 for the six trials it took to find this configuration, the edge no longer clears the bar. The gap between the gaudy fold Sharpes (1.9–2.5) and the full-period 0.65 is itself a warning: stitch the folds together and a 20.48% max drawdown appears that none of the individual windows showed.
Strengths and risks
Strengths: a clean, defensible thesis; four-for-four positive folds; low turnover-adjusted fees; and genuinely strong recent-period out-of-sample numbers.
Risks: the headline Sharpe of 0.65 is mediocre, the 20.48% drawdown is steep for a $10k book, and the deflated Sharpe says much of the apparent edge may be the product of trial-and-error fitting. The reported win rate of 0 across five trades reflects positions that are still open rather than losing round-trips — but it means we have no realised evidence yet. Combine that with a cash-starved live account rejecting every new signal, and the honest verdict is: promising shape, unproven edge. Keep it on the leaderboard, keep it off the real-money council until it clears validation and demonstrates it can actually trade.