Thesis
momentum-code runs a simple, legible idea: buy the top positive movers across a 24-name universe of large-cap US equities — spanning tech (AAPL, MSFT, NVDA), financials (JPM, BAC, V), healthcare (JNJ, UNH, PFE), staples (PG, KO, WMT), and energy (XOM, CVX) — with a per-position cap to limit concentration. It is a classic cross-sectional momentum tilt, and its transparency is a genuine strength: there is little black-box behavior to second-guess.
Backtest Performance
Over 451 days the strategy returned 19.76%, lifting simulated equity to $11,976 and implying a 10.6% CAGR. That headline number is respectable, but the risk-adjusted picture is more sober: a Sharpe of 0.65 against a 20.48% maximum drawdown means investors would have needed to stomach a one-fifth peak-to-trough decline for those gains. Turnover of 92.74% is moderate, and fees were negligible at $5. Note the reported win rate of 0 across just 5 trades — with only executed buys and no recorded round-trip exits, this reflects an absence of closed positions rather than five losing bets, but it does underline how thin the trade sample is.
Validation
This is where the story gets more encouraging — and more nuanced. Across four walk-forward folds, all four were positive (15.38%, 3.27%, 12.18%, 13.71%), with out-of-sample return of 13.71% and an OOS Sharpe of 1.93. Consistency across regimes is exactly what you want to see. Yet the formal gate did not pass. The deflated Sharpe ratio (DSR) sits at just 0.338 against a probabilistic Sharpe (PSR) of 0.811, and the run drew on 6 trials. The gap between a healthy PSR and a weak DSR is the multiple-testing penalty at work: once you account for how many configurations were tried, confidence in a true edge thins considerably. Four positive folds is promising, not conclusive.
Recent Activity
Here lies the most pressing concern. The strategy last executed trades on June 1 (buys in XOM, NVDA, BAC, and late-May adds in HON, MSFT). Since then, its six most recent scheduled runs (July 24–31) all report 0 executed and multiple rejections per run, with cash frozen at $608.79. Portfolio value has drifted between roughly $10,085 and $10,373 on price moves alone, not new positioning. In other words, the live book is effectively static — the signal is generating candidates, but the per-position caps or available cash are blocking every order.
Balance of Evidence
Strengths: an interpretable thesis, consistently positive folds, and a strong OOS Sharpe. Risks: a failed validation gate, a punishing 20%+ drawdown, a tiny trade count that limits statistical confidence, and — most immediately — an execution pipeline that has placed no trades in over a week. momentum-code is worth watching, but the rejected-order backlog needs diagnosing before its backtest promise can be trusted live.