Thesis and Universe
momentum-code follows a straightforward premise: at each rebalance, identify the top positive movers across a 24-name large-cap universe — tech, financials, healthcare, consumer staples, energy, and industrials — and build an equal-weighted position in each, capped per holding to limit concentration risk. The logic is mechanical and transparent, which makes it easy to audit and a clean baseline against which more complex strategies can be measured.
Backtest Overview
Over 451 days of simulation the strategy compounded to +19.76% total return, implying a CAGR of roughly 10.6%. The full-period Sharpe of 0.65 is modest but not dismissible for a rules-based system with only five trades and $5 in total fees. Turnover came in at 92.74%, consistent with a momentum approach that rotates aggressively when the signal flips.
The headline risk figure demands attention: a 20.48% maximum drawdown over the backtest window is meaningful, particularly because the strategy holds a concentrated pocket of large-caps rather than a diversified basket. Traders evaluating position sizing should weight this figure seriously.
The reported win rate of 0% reflects a data artefact of the five-trade sample rather than a genuine edge-free record — with so few round-trips it is simply too small a sample to interpret directionally.
Walk-Forward Validation
The more instructive picture comes from the four-fold walk-forward analysis:
| 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 — an encouraging consistency signal. Three of the four produced Sharpe ratios above 1.9, and the most recent out-of-sample fold (Fold 4, which coincides with the live period) returned +13.71% with a Sharpe of 1.93 and a contained drawdown of 6.32%. That is the kind of out-of-sample behaviour that suggests the signal has real structure.
Fold 2 is the outlier: a volatile first half of 2025 pushed the drawdown to 16.55% and compressed risk-adjusted returns sharply. Understanding what drove that regime — whether macro, sector rotation, or signal degradation — would materially strengthen the strategy's risk model.
Validation Gate
Despite the positive fold count, momentum-code has not passed Headmars' automated validation gate. The key sticking point is the Deflated Sharpe Ratio of 0.338, which corrects for the fact that six parameter trials were run. The PSR of 0.811 (probability that the true Sharpe exceeds zero) is reassuring, but the DSR penalises the trial count and leaves meaningful uncertainty about whether the observed edge survives multiple-testing correction. Until DSR clears the threshold, the strategy remains in monitored paper-trading rather than advancing to a higher capital allocation tier.
Recent Activity
Live execution has been quiet. The last confirmed trades were a cluster of buys on 31 May and 1 June — XOM, NVDA, BAC, HON, and MSFT — with the portfolio sitting at $9,712 as of 15 June. Every scheduled run since 8 June has resulted in zero executions and one to two rejections, suggesting the momentum filter is not finding qualifying candidates above its threshold in the current tape. The strategy is holding cash ($608.79) and waiting for a clear signal rather than forcing trades.
Outlook
momentum-code is a disciplined, auditable baseline with genuine walk-forward evidence in its favour. The path to clearing the validation gate likely runs through either reducing the trial count in the parameter search or accumulating more live fold data to drive down the DSR penalty. The Fold 2 regime deserves post-mortem attention before the strategy is given wider exposure.