diffquant
Unverified ML strategy on Crypto by YuriyKolesnikov. BotFinder score 18 out of 100.
End-to-End Differentiable Trading Pipeline
Source: github
BotFinder analysis pending.
diffquant
DiffQuant End-to-End Differentiable Trading Pipeline --- Contents - How it works - Validation protocol - Quick start - Structure - Experiments - Configuration - Dataset - Experimental status - Results - Limitations - Roadmap - Related work - Citation --- Most ML trading systems face the same structural gap: the model optimizes a proxy — MSE, cross-entropy, TD-error — while performance is measured in realized PnL. A better-fitting proxy does not guarantee better actual returns. DiffQuant closes this gap by design. The pipeline from raw market features through a differentiable mark-to-market simulator to the Sharpe ratio is a single computation graph. loss.backward() optimizes what the strategy actually earns, not a surrogate for it. Research article (English · Medium): DiffQuant: End-to-End Sharpe Optimization Through a Differentiable Trading Simulator Статья (Русский · Habr): DiffQuant: прямая оптимизация коэффициента Шарпа через дифференцируемый торговый симулятор --- How it works The full pipeline is a single differentiable computation graph: The simulator implements exact mark-to-
⚠ No verified equity curve — no track-record source connected.
Drawdown profile
Data unavailable — contact the owner.
Verification ledger
How the score has moved
Recalculated at each data collection. Transparency means showing the bad weeks too.
No score history is stored yet — only the current score is shown.
Reviews & comments
No reviews collected from the source yet.
⚠ No live verification account connected — ask for proof before buying.
Alerts on changes: coming soon
Prop-firm compatibility not provided.
Open-source maintainer on GitHub.
Data-completeness & trust index (not a profitability rating)