Strategy Overview
momentum-code is one of Headmars' hand-authored baseline strategies: each scheduled run scans a 24-stock universe of large-cap US names — spanning tech, financials, healthcare, consumer, energy, and industrials — and buys the top positive movers, subject to a per-position cap. The logic is deliberately simple, which makes it a useful benchmark against which more complex, LLM-authored strategies can be measured.
The strategy was approved with a risk score of 0 and deployed on 31 May 2026 with a $10,000 paper allocation.
Recent Activity
Deployment opened with three buys: MSFT (4 shares @ $450.24), HON (8 @ $237.86), and BAC (38 @ $51.60), leaving roughly $4,335 in cash. The following day added NVDA (8 @ $224.20) and XOM (13 @ $148.69), bringing total equity to $10,033.
Since then, the strategy has gone quiet. Runs on 2 June through 4 June executed zero trades — with 1–3 signals rejected each day — as the portfolio held near $9,850–$9,994. That contraction from the 1 June peak reflects normal mark-to-market noise at this early stage, not a structural drawdown. Cash of $608.79 remains deployed and ready for the next qualifying mover.
Backtest & Validation Performance
Over 451 days of backtesting, momentum-code returned 19.76% on a starting equity of $10,000 (final equity $11,976), implying a CAGR of ~10.6%. The overall Sharpe of 0.65 is modest but not dismissible for a strategy with this simplicity.
The walk-forward validation across four folds tells a more nuanced story:
| Fold | Period | Return | Sharpe | Max DD |
|---|---|---|---|---|
| 1 | Aug 2024 – Jan 2025 | +15.38% | 2.47 | 6.12% |
| 2 | Jan 2025 – Jul 2025 | +3.27% | 0.46 | 16.55% |
| 3 | Jul 2025 – Dec 2025 | +12.18% | 2.31 | 5.21% |
| 4 | Dec 2025 – May 2026 | +13.71% | 1.93 | 6.32% |
All four folds are positive — a meaningful result. The out-of-sample Sharpe of 1.93 in fold 4 is the strongest of the set, and the out-of-sample return of 13.71% compares favourably to the full-backtest figure, suggesting the strategy isn't just fitting to the training window.
Why Validation Failed
Despite the clean fold record, the overall validation flag is not passed. The culprit is the Deflated Sharpe Ratio (DSR = 0.338), which adjusts for the number of trials tested (6 in this case). When a strategy is iterated even a handful of times, the probability that a positive Sharpe arose by chance rises meaningfully. A DSR below ~0.95 is the platform's threshold for statistical confidence, and 0.338 falls well short.
The Probabilistic Sharpe Ratio (PSR = 0.811) paints a slightly better picture — there's roughly an 81% chance the true Sharpe exceeds zero — but the trial-count penalty pushes the composite result below the bar.
Strengths and Risks
Strengths: Consistent positive folds, a live portfolio that opened cleanly, low fee drag ($5 total), and a simple thesis that is easy to audit. The high-Sharpe folds (1 and 3) demonstrate that momentum can work in trending environments.
Risks: Fold 2's 16.55% drawdown and 0.46 Sharpe signal that choppy or mean-reverting markets punish this approach. The 92.74% backtest turnover is high and will amplify slippage in live conditions beyond the paper-trading context. And the DSR failure is a genuine red flag — six trials is a low bar, and the strategy hasn't yet earned statistical credibility.
Bottom Line
momentum-code is a sensible, readable baseline that demonstrates the Headmars validation pipeline catching what raw returns miss. Watch fold 4's live continuation through Q3 2026: if the out-of-sample Sharpe holds above 1.5 with a drawdown below 10%, the case for promotion strengthens considerably.