Thesis
momentum-code runs a simple, legible premise: buy the top positive movers in a 24-name large-cap universe (AAPL, MSFT, NVDA, JPM, XOM and friends), with a cap on each position. There is no attempt at cleverness here — it rides what is already going up and limits concentration. Simple theses are easy to audit, which is a point in its favour.
Backtest Performance
Over 451 days the strategy turned a starting balance into $11,976.21 — a 19.76% total return, roughly 10.6% CAGR. The Sharpe is a modest 0.65, and the max drawdown of 20.48% is almost as large as the whole return, so this is not a smooth ride. Turnover sits at 92.74% on just 5 trades and $5 in fees, so costs are not the story. Note the reported win rate of 0%: with only five trades, most of which look like still-open positions, that figure is an artefact of too few closed round-trips rather than a run of losers — treat it as noise, not signal.
Validation
This is where the picture gets interesting. Across four walk-forward folds, all four were positive (15.38%, 3.27%, 12.18%, 13.71%), with the most recent out-of-sample fold returning 13.71% at a healthy 1.93 Sharpe. Several folds printed Sharpes above 2.0. On the surface, encouraging.
Yet the validation gate reports passed: false. The deflated Sharpe ratio (DSR) is only 0.338, dragged down by 6 trials of multiple-testing adjustment, even though the probabilistic Sharpe (PSR) is a strong 0.811. The honest read: the strategy looks good, but once you penalise for how many variants were tried to find it, the statistical confidence thins out. The gate is right to hold the line.
Recent Activity — The Real Concern
The operational story is worse than the stats. The last executed trades were in late May and early June 2026 (buys in MSFT, HON, BAC, NVDA, XOM). Since then, nothing has filled. The last six scheduled runs (21–28 October) all report 0 executed, 1–2 rejected, with cash frozen at $608.79 and portfolio value drifting between roughly $10,375 and $10,533.
That pattern — persistent rejections with low idle cash — suggests the engine wants to trade but cannot afford the capped position sizes, so it sits on its hands. A momentum strategy that stops rotating stops being a momentum strategy.
Verdict
Promising economics, genuine out-of-sample consistency, but two unresolved flags: a validation gate it hasn't cleared, and a live book that has effectively seized up. The numbers earn a second look; the plumbing needs a fix first.