MatFinProtocol • Live backtest leaderboard

Financial Asset Forecasting & Trading Leaderboard

Protocol‑compliant backtests evaluated under consistent, cost‑aware conditions. Each row corresponds to a published or reproducible AI‑based strategy benchmarked under MatFinProtocol.

Higher is better: Annualised profit, Sharpe Lower is better: Max drawdown % All strategies net of costs & slippage (per protocol)
MatFinProtocol Leaderboard
Click column headers to sort · Type to filter · Maintained by Dr Matloob Khushi – about & contact
Last updated: 2026‑03‑08
Reference ⇅ Initial balance⇅ Final balance⇅ % annualised profit⇅ % max drawdown⇅ Sharpe ratio⇅ Backtest period⇅ Total trades⇅ Win rate %⇅ Model / notes⇅
Khushi (2026), “MatFinProtocol: Minimum Reporting and Evaluation Standards…” 100,000 153,400 +9.8 ‑12.3 1.45 2016‑01‑01 → 2024‑12‑31 4,120 57.2 Reference protocol strategy
Zhang & Khushi (2020), “GA‑MSSR: Genetic Algorithm Maximizing Sharpe and Sterling Ratio…” 100,000 187,900 +13.4 ‑19.7 1.68 2010‑01‑01 → 2019‑12‑31 2,305 61.0 SS Ratio‑optimised GA

Only studies that satisfy MatFinProtocol (no leakage, cost‑aware backtesting, full risk reporting) are eligible for inclusion. Values are harmonised to a common reporting schema to support investor‑relevant comparison.