- Implemented `generate_bridge_csv.py` to generate reports for strategy winners from the Strategy Tester notebook.
- Added `smoke_test_explorer.py` to perform smoke tests on the Explorer notebook integration, validating core logic and data processing.
- Introduced `test_lifecycle_parity.py` to verify event timelines between live and backtest evaluations, ensuring consistent activation, partial close, scalp exit, and regime shift behaviors across different timeframes.
- Added `test_lifecycle_units.py` for unit testing of lifecycle configurations, including cent normalization, activation thresholds, and the absence of R-multiple fields.
- Created `test_three_state_contract.py` to enforce and validate the three-state regime (TREND, MEAN_REVERSION, VOLATILITY_SHOCK) across various components, ensuring that any attempt to use more than three states raises appropriate errors.
- Integrated regime model predictions into the validation process, allowing for fallback to ensemble models.
- Updated validation criteria to include checks for maximum drawdown, minimum trades, and MR leaks.
- Enhanced test suite to cover new validation scenarios and ensure robustness of strategy evaluation.
- Adjusted signal pipeline audit tests to reflect changes in regime handling and validation logic.
- Implemented `add_specialized_features` to compute ATR moving averages, expansion ratios, realized volatility ratios, and session proximity features.
- Integrated the new feature set into the processing pipeline.
- Updated `run_sensitivity` to utilize new Z-score thresholds from `SignalEngine`.
- Refactored `SignalEngine` to include a unified `SignalDecision` class for consistent entry/exit logic.
- Enhanced `evaluate_bar` to incorporate dynamic probability thresholds and M15 entry gates.
- Added comprehensive tests for signal generation, decision parity, and dynamic thresholds.
- Updated `get_feature_cols` to handle one-hot encoding for HMM states in M5/M15.
- Modified `prepare_features` to include a rolling median for HMM states and drop the original integer state.
- Enhanced `compute_live_features` to generate one-hot encoded features for M5/M15 and retain the integer state for H1.
- Implemented runtime checks to ensure live feature keys match training columns, raising errors for mismatches.
- Adjusted scoring logic in `optimizer.py` to apply log-loss for M5/M15 and backtest for H1, improving robustness against over-regularization.
- Implemented auto-sync for raw CSV data from MT5 in cmd_optimize, ensuring missing bars are appended if the terminal is running.
- Added ensure_data_updated function in mt5_sync.py to check and fetch missing bars for specified timeframes, logging warnings if MT5 is unavailable.
- Introduced median filtering in engine_hmm.py to smooth HMM state predictions, reducing noise from regime flips.
- Updated predict_states to apply median filtering after state remapping for consistency.
- Added time-of-day gating in processor.py to filter out Asian-session bars, retaining only London/NY high-liquidity hours for analysis.
- Removed obsolete model configuration file `stage1_m15_headway_cent.json`.
- Updated database file `study_headway_cent.db` to reflect changes in model parameters.
- Enhanced backtester to utilize dynamic ATR bands and synth VIX z-score for entry signals.
- Modified engine to include new features: `atr_band_position` and adjusted feature importance.
- Implemented dynamic ATR band calculations in the processor module.
- Adjusted signal engine logic to incorporate new thresholds for trend and mean-reversion entries based on ATR bands and z-scores.
- Updated optimizer parameters for improved model performance.
- Removed redundant `gmm_vol_cluster` feature from XGBoost training to improve efficiency.
- Adjusted feature selection for bucket models in `train_xgb_ensemble`.
- Updated probability thresholds for trading signals to enhance decision-making.
- Standardized exit confirmation bars for different timeframes in the signal engine.
- Added `--stage` argument to `cmd_optimize` for selecting between Stage-1 (XGB exploration) and Stage-2 (CPCV optimization).
- Introduced `run_optimization_stage1` for fast single hold-out XGB trials, significantly improving optimization speed.
- Updated `run_optimization` to support warm-starting from Stage-1 best parameters.
- Enhanced logging with dedicated score logging for trial monitoring.
- Adjusted hyperparameter ranges for XGBoost to allow deeper trees and finer splits.
- Added synthetic VIX feature computation to the feature application process.
- Persisted best parameters from Stage-1 to JSON for future use in Stage-2.
- Updated documentation for new optimization stages and usage instructions.
- Added a cooldown period to prevent immediate re-entries after a trade, reducing churn in rapidly oscillating regimes.
- Simplified exit conditions by removing ATR trailing, partial close, and profit guard during optimization.
- Adjusted minimum confirmation bars for H1 to enhance stability before entries and exits.
- Lowered the floor for reg_lambda in optimizer to allow for better HMM state signals.
- Implemented a regime oscillation guard in the CPCV execution to skip paths with excessive transitions, mitigating potential drawdowns.
- Bump optimizer version from 3.6 to 3.7.
- Refactor make_objective function to use Combinatorial Purged Cross-Validation (CPCV) instead of WFO.
- Implement execute_cpcv function for CPCV analysis with strict HMM and scaler fitting.
- Update run_wfa to utilize CPCV and maintain backward compatibility with WFO key aliases.
- Remove deprecated WFO-related code and metrics, replacing them with CPCV equivalents.
- Enhance logging for CPCV trials and results.
- Removed the early stopping guard fold in the XGBoost training process to enhance model generalization.
- Updated optimizer version to 3.6 and adjusted search space for regularization parameters (reg_alpha and reg_lambda) to prevent overfitting.
- Implemented a purged inner cross-validation split to avoid leakage between training and validation sets.
- Adjusted scoring penalties for WFE to better reflect model performance discrepancies.
Luke Mosoti