The thesis
momentum-code runs a simple, well-worn idea: buy the top positive movers across a 24-name universe of US large caps — the megacap tech complex, financials, staples, healthcare and energy — with a cap on each position. It is momentum in its most literal form, and the strategy is currently flagged live.
Recent activity
The picture on the ground is one of a portfolio that has stopped moving. The last executed trades landed on 31 May and 1 June 2026 — a cluster of buys in XOM, NVDA, BAC, HON and MSFT. Since then, every scheduled run has come back the same way: zero executed, one to three rejected. Across 31 August through 7 September, cash has sat frozen at $608.79 while total equity drifted in a narrow band around $10,500–$10,671.
That pattern is telling. With only ~$609 of dry powder, the strategy simply cannot fund the positions its ranking logic wants to open, so orders are rejected rather than filled. momentum-code is not choosing to stand pat — it is fully invested and out of room. This is a capital-allocation constraint, not a signal of conviction.
Backtest and validation
The headline backtest is respectable: +19.76% total return over 451 days, a 10.6% CAGR, and a final equity of $11,976 on a small $5 fee base. But the quality metrics temper the enthusiasm. The Sharpe of 0.65 is modest, and the 20.48% max drawdown is a real drag — investors sat through a fifth of the portfolio evaporating to earn that return. Turnover near 93% is high for a five-trade sample, and the reported 0% win rate reflects positions still open rather than realized losers.
The cross-validation is the more encouraging story. All four folds were positive (+15.4%, +3.3%, +12.2%, +13.7%), with fold-level Sharpes as high as 2.47 and, crucially, an out-of-sample return of 13.71% at a 1.93 Sharpe on the most recent fold. The probabilistic Sharpe ratio of 0.811 is healthy.
And yet the validation gate reads passed: false. The likely culprit is the deflated Sharpe ratio of 0.338 — once you adjust for the six trials run, the evidence that this edge is real, rather than the best of several attempts, is thin. That is the right kind of skepticism to apply to any momentum backtest.
The balance
Strengths: a coherent thesis, consistently positive folds, and strong recent out-of-sample behaviour. Risks: a deep drawdown, a modest full-sample Sharpe, a validation gate the strategy did not clear, and — most immediately — an operational problem where a near-empty cash balance is quietly turning the signal off.
The near-term priority is not the model but the plumbing: momentum-code needs either a rebalancing rule that frees cash or a capital top-up before its live behaviour can honestly test what the folds promise.