## ⚙️ Strategy Configuration | Parameter | Value | Description | |-----------|-------|-------------| | `strategy` | `Bollinger_w10_std1.5` | Trading strategy name | | `symbol` | `EURUSD` | Trading instrument | | `account_name` | `FUNDEDNEXT_STLR2_6K` | Trading account identifier | | `bar_type` | `tick` | Bar type (tick/volume/time/dollar/...) | | `bar_size` | `M1` | Bar timeframe | | `price` | `mid_price` | Price type (bid/ask/mid) | | `target_lookback` | `20` | Target calculation lookback periods | | `profit_target` | `1` | Profit target in risk multiples | | `stop_loss` | `2` | Stop loss in risk multiples | | `max_holding_period` | `{"days": 1}` | Maximum holding period | | `min_ret` | `0` | Minimum return threshold | | `vertical_barrier_zero` | `True` | Vertical barrier at zero crossing | | `filter_as_series` | `False` | Filter as time series | --- # 📊 Hyperparameter Tuning Analysis Report *Generated on: 2026-05-03 15:37:00* ## 🎯 Executive Summary ### Key Findings - **Best Model Performance**: `0.7984 ± 0.0101` - **Risk Level**: `LOW` > ✅ **Excellent**: Model shows high consistency across validation folds. ## 📈 Main Visualization ### Hyperparameter Analysis Overview ## 📊 Performance Overview **Total Models Evaluated**: `36` **Performance Range**: `0.7984` - `0.6039` **Average Performance**: `0.7040 ± 0.0599` ## 🏆 Top Models Comparison | Rank | Mean Score | Std Score | Fit Time (s) | Efficiency | |------|------------|-----------|--------------|------------| | 1 | `0.7984` | `0.0101` | `2.35` | `0.34` | | 2 | `0.7977` | `0.0418` | `2.05` | `0.39` | | 3 | `0.7970` | `0.0172` | `2.71` | `0.29` | | 4 | `0.7970` | `0.0232` | `3.77` | `0.21` | | 5 | `0.7963` | `0.0150` | `2.10` | `0.38` | ## 🛡️ Stability Analysis **Models meeting stability threshold**: `23` ### Best Stable Model - **Score**: `0.7984` - **Standard Deviation**: `0.0101` ## ⏱️ Time-Efficiency Analysis ### Training Time Statistics - **Fastest Model**: `0.62s` - **Slowest Model**: `4.92s` - **Average Time**: `3.01s` - **Median Time**: `3.20s` ## 📊 Hyperparameter Trends ### Parameter Impact Analysis #### n_estimators | Value | Mean Score | Score Std | Count | Avg Time (s) | |-------|------------|-----------|-------|--------------| | `200` | `0.7277` | `0.0559` | `12` | `2.91` | | `50` | `0.6963` | `0.0684` | `12` | `3.36` | | `100` | `0.6881` | `0.0514` | `12` | `2.76` | #### max_depth | Value | Mean Score | Score Std | Count | Avg Time (s) | |-------|------------|-----------|-------|--------------| | `7` | `0.7207` | `0.0473` | `9` | `3.05` | | `3` | `0.7136` | `0.0549` | `9` | `3.08` | | `10` | `0.6928` | `0.0821` | `9` | `2.34` | | `5` | `0.6889` | `0.0536` | `9` | `3.57` | #### min_samples_split | Value | Mean Score | Score Std | Count | Avg Time (s) | |-------|------------|-----------|-------|--------------| | `2` | `0.7239` | `0.0555` | `12` | `2.88` | | `5` | `0.7026` | `0.0469` | `12` | `3.23` | | `10` | `0.6857` | `0.0730` | `12` | `2.93` | ## 🎯 Model Selection Recommendations ### Final Recommendation ### Recommended Hyperparameters ```python n_estimators = 50 max_depth = 10 min_samples_split = 10 ``` ## 🔍 Specific Insights ### Model Architecture Analysis **Overall Performance**: `EXCELLENT` **Stability Rating**: `HIGH` ### Best Model Details - **max_depth**: `10` - **n_estimators**: `50` - **mean_test_score**: `0.7984` - **Standard Deviation**: `0.0101` - **Training Time**: `2.35s` ## 💼 Practical Trading Implications ### Performance Expectations - **Expected Win Rate**: `~79.8%` - **Performance Consistency**: `High` - **Risk Assessment**: `LOW` ### Trading Strategy Considerations > ✅ **Stable Strategy Detected** > - Can consider standard position sizing > - Strategy likely to perform consistently > - Lower monitoring frequency acceptable ## 📋 Detailed Results ### Complete Results (Top 10 Models) | Rank | mean_test_score | std_test_score | mean_fit_time | n_estimators | max_depth | min_samples_split | | --- | --- | --- | --- | --- | --- | --- | | 1 | `0.7984` | `0.0101` | `2.35s` | `50` | `10` | `10` | | 2 | `0.7977` | `0.0418` | `2.05s` | `200` | `7` | `10` | | 3 | `0.7970` | `0.0172` | `2.71s` | `200` | `10` | `10` | | 4 | `0.7970` | `0.0232` | `3.77s` | `50` | `3` | `2` | | 5 | `0.7963` | `0.0150` | `2.10s` | `200` | `10` | `2` | | 6 | `0.7807` | `0.0244` | `1.68s` | `100` | `3` | `2` | | 7 | `0.7559` | `0.0396` | `2.35s` | `200` | `7` | `2` | | 8 | `0.7552` | `0.0329` | `2.88s` | `200` | `5` | `2` | | 9 | `0.7551` | `0.0322` | `4.60s` | `50` | `7` | `5` | | 10 | `0.7414` | `0.0369` | `2.02s` | `50` | `3` | `5` | ## 📚 Appendix ### A. Glossary - **Mean Test Score**: Average performance across CV folds - **Std Test Score**: Standard deviation across CV folds - **Mean Fit Time**: Average training time per model - **Stability Threshold**: Maximum acceptable std (default: 0.03) - **Efficiency Score**: Performance per unit of training time ### B. Analysis Methodology 1. **Cross-Validation**: Typically 5-fold stratified CV 2. **Scoring Metric**: mean_test_score 3. **Hyperparameter Search**: GridSearch/RandomizedSearch 4. **Stability Analysis**: Models with std ≤ 0.03 considered stable 5. **Time Efficiency**: Pareto frontier analysis --- *Report generated by Hyperparameter Analysis Module*