2 Commits

Author	SHA1	Message	Date
Nicholai	3621d93643	feat(backtest): optimize exit strategy and position sizing ... 6 iterations of backtest refinements with key discoveries: - stop losses don't work for prediction markets (prices gap) - 50% take profit, no stop loss yields +9.37% vs +4.04% baseline - diversification beats concentration: 100 positions → +18.98% - added kalman filter, VPIN, regime detection scorers (research) exit config: take_profit 50%, stop_loss disabled, 48h max hold position sizing: kelly 0.40, max 30% per position, 100 max positions	2026-01-22 11:16:23 -07:00
Nicholai	025322219c	feat: initial commit with code quality refactoring ... kalshi prediction market backtesting framework with: - trading pipeline (sources, filters, scorers, selectors) - position sizing with kelly criterion - multiple scoring strategies (momentum, mean reversion, etc) - random baseline for comparison refactoring includes: - extract shared resolve_closed_positions() function - reduce RandomBaseline::run() nesting with helper functions - move MarketCandidate Default impl to types.rs - add explanatory comments to complex logic	2026-01-21 09:32:12 -07:00