Loading…
A 3-year out-of-sample backtest of the exact strategy code that trades live, on real hourly market data across 15 liquid assets, with realistic execution costs. The strategy parameters were fixed in advance — not fitted to this data.
Illustration from the 3-year out-of-sample backtest with costs included. Backtested results do not guarantee future performance; trading involves substantial risk of loss.
Same code, backtest and live. The portfolio construction that produced this curve is the exact module the live engine runs — they cannot drift apart.
No curve-fitting. The strategy parameters come from decades-old trend-following literature, fixed before this data was seen — what you see is genuine out-of-sample behavior, including a full bear market.
Costs included. Every rebalance is charged realistic execution costs. Profitable each calendar year of the test window.
Backtested performance has inherent limitations and does not represent actual trading. Markets change; future results may differ materially. Trading involves substantial risk of loss. This is not investment advice — see our Terms & Risk Disclosure.