2 commits

Author	SHA1	Message	Date
Claude	3fcdbe48c1	perf(neural-trader): optimize backtesting and risk management ... Backtesting: - Single-pass metrics calculation (was 10+ passes) - Inline stats: mean, variance, win/loss counts computed together - Combined drawdown metrics in one pass - Removed redundant method calls Risk Management: - Ring buffers for trade history (O(1) vs O(n) shift/slice) - Running sum for volatility average (O(1) vs O(n) reduce) - Incremental loss count tracking Reduces iteration overhead by ~5-10x for large datasets.	2025-12-31 17:19:03 +00:00
Claude	bca9855278	feat(neural-trader): add integrated trading system ... Components: - DAG-based trading pipeline (4.6ms latency) • Parallel execution of LSTM, Sentiment, DRL • Signal fusion with configurable weights • Kelly-based position sizing - Backtesting framework • Sharpe, Sortino, Calmar ratios • Max drawdown, VaR, CVaR • Walk-forward analysis • Comprehensive trade statistics - Real data connectors • Yahoo Finance (free, historical) • Alpha Vantage (sentiment, intraday) • Binance (crypto, WebSocket) • Rate limiting, caching, retry logic - Risk management layer • Position limits (10% max per position) • Stop-losses (fixed, trailing, volatility) • Circuit breakers (drawdown, loss rate) • Exposure management (leverage control)	2025-12-31 17:02:40 +00:00