Thesis
momentum-code runs a simple, legible idea: buy the top positive movers across a 24-name large-cap universe — Apple, Microsoft, Nvidia, JPMorgan, Exxon and peers — with a cap per position to avoid concentration. It's a classic cross-sectional momentum tilt, and its transparency is a genuine strength: there's little room for the kind of black-box overfitting that plagues denser signals.
Backtest and Validation
Over 451 days the backtest returned 19.76% (final equity $11,976), a 10.6% CAGR, with a Sharpe of 0.65 and a max drawdown of 20.48%. Turnover was moderate at 92.74% and fees negligible ($5). The headline return is respectable, but the Sharpe and the 20%+ drawdown make clear this is a return earned with real volatility, not a smooth ride.
The walk-forward picture is more encouraging. Across four folds, all four were positive (15.38%, 3.27%, 12.18%, 13.71%), and the out-of-sample segment delivered 13.71% at a 1.93 Sharpe — notably better risk-adjusted performance than the full-sample number. The Probabilistic Sharpe Ratio sits at a solid 0.811.
And yet validation failed. The Deflated Sharpe Ratio — which discounts for the six trials run — comes in at just 0.338, below the bar. In plain terms: once you penalise for how many variants were tested, the evidence that this edge is real rather than lucky is thin. Four positive folds are reassuring; a sub-0.35 DSR is the system correctly refusing to over-trust them.
Recent Activity
Here the story turns cautionary. The last executed trades were a cluster of buys at the end of May and start of June 2026 — XOM, NVDA, BAC, HON, MSFT. Since then, every scheduled run from 18–25 August executed zero trades and rejected one or two orders each. Cash has been pinned at $608.79 throughout, while total account value drifted down from $10,705 to $10,469 over that week — a slow bleed on existing positions with no new action taken.
A reported win rate of 0% across only 5 trades is almost certainly an artefact of open, unrealised positions rather than five outright losers, but it underscores how little closed evidence exists live.
Balance of Risks
Strengths: an interpretable thesis, uniformly positive folds, and strong OOS risk-adjusted returns. Risks: a failed DSR gate warning of possible selection bias, a persistent stream of rejected orders that suggests a sizing or liquidity constraint is quietly blocking the strategy, and a live equity curve currently ticking downward.
momentum-code looks like a promising candidate held back by an honest validation layer and a live plumbing issue worth investigating. The out-of-sample numbers earn it continued observation — but not yet conviction.