跳到主要內容

Feature Iteration Run #1009: zz_sylvain

Status: completed | Started: 2026-07-26 11:17:53 | Ended: 2026-07-26 11:26:15

📊 Iterations

Iter Y Label Model Warm Proxy Parent FS Feature DSL DSL Valid Baseline PF Modified PF Scalar Score t-stat p-value Cohen's d Result Reason
1 C8 gradient_boosting — — #7 k_loop_iter_1_646216 k_high.pct_change(12) * (1 - price_posi… ✅ 1.947 1.487 -0.1508 0.000 0.702 0.124 ❌ REJECT scalar_score -0.1508 <= 0.0, sharpe_delta -5.0829 < -0.3, hypothesis test not confirmed
2 C8 gradient_boosting — — #7 k_iter2_k_high_pct_change_hl_range_dist_to_low k_high.pct_change(12) * (1 + hl_range) … ❌ 0.000 0.000 0.0000 0.000 1.000 0.000 ❌ REJECT quality_gate: C8 leakage: ['dist_to_low']
3 C8 gradient_boosting — — #7 k_iter3_price_position_atr_norm obv_ensemble_3 * (1 - price_position) /… ❌ 0.000 0.000 0.0000 0.000 1.000 0.000 ❌ REJECT quality_gate: canonical duplicate: obv_ensemble_3 * (1 - price_position) / (1 + atr_norm * 10)
4 C8 gradient_boosting — — #7 k_iter4_k_high_pct_change_hl_range_price_position k_high.pct_change(12) * (1 + hl_range) … ❌ 0.000 0.000 0.0000 0.000 1.000 0.000 ❌ REJECT quality_gate: canonical duplicate: k_high.pct_change * (1 + hl_range) * (1 - price_position) / (1 + atr_norm)
5 C8 gradient_boosting — — #7 k_loop_iter_5_b45423 k_momentum_pct_change / (1 + i_atr(k_hi… ✅ 1.947 1.243 -0.3300 0.000 0.386 0.344 ❌ REJECT scalar_score -0.3300 <= 0.0, sharpe_delta -11.5169 < -0.3, hypothesis test not confirmed
6 C8 gradient_boosting — — #7 k_loop_iter_6_d72047 o_div_amplitude_12 * k_high.pct_change(… ✅ 1.947 1.138 -0.4196 0.000 0.512 0.261 ❌ REJECT scalar_score -0.4196 <= 0.0, sharpe_delta -14.6732 < -0.3, hypothesis test not confirmed
7 C8 gradient_boosting — — #7 k_loop_iter_7_e0bda4 obv_ensemble_3 * k_high.pct_change(12) … ✅ 1.947 1.138 -0.4196 0.000 0.512 0.261 ❌ REJECT scalar_score -0.4196 <= 0.0, sharpe_delta -14.6732 < -0.3, hypothesis test not confirmed
8 C8 gradient_boosting — — #7 k_iter8_pct_change_price_position_atr_norm obv_rebased.pct_change(12) * (1 - price… ❌ 0.000 0.000 0.0000 0.000 1.000 0.000 ❌ REJECT safe_eval DSL produced inf values; likely division by zero
9 C8 gradient_boosting — — #7 k_iter9_i_rsi_k_close_price_position_vol_ratio i_rsi(k_close, 14) * (1 - price_positio… ❌ 0.000 0.000 0.0000 0.000 1.000 0.000 ❌ REJECT quality_gate: NaN ratio 1.000 exceeds 0.3
10 C8 gradient_boosting — — #7 k_loop_iter_10_5e3f44 k_high.pct_change(12) / (1 + atr_norm) … ✅ 1.947 1.138 -0.4196 0.000 0.512 0.261 ❌ REJECT scalar_score -0.4196 <= 0.0, sharpe_delta -14.6732 < -0.3, hypothesis test not confirmed
11 C8 gradient_boosting — — #7 k_loop_iter_11_bdf5db obv_ensemble_3 * (1 - price_position) /… ✅ 1.947 1.085 -0.4789 0.000 0.463 0.243 ❌ REJECT scalar_score -0.4789 <= 0.0, sharpe_delta -16.8215 < -0.3, hypothesis test not confirmed
12 C8 gradient_boosting — — #7 k_iter12_k_high_pct_change_i_rsi_k_close (k_high.pct_change(12) - i_rsi(k_close,… ❌ 0.000 0.000 0.0000 0.000 1.000 0.000 ❌ REJECT quality_gate: NaN ratio 1.000 exceeds 0.3
13 C8 gradient_boosting — — #7 k_loop_iter_13_657217 i_macd(k_close, 12, 26, 9) * (1 - price… ✅ 1.947 1.784 -0.4560 0.000 0.212 0.534 ❌ REJECT scalar_score -0.4560 <= 0.0, sharpe_delta -2.5358 < -0.3, hypothesis test not confirmed
14 C8 gradient_boosting — — #7 k_loop_iter_14_28fa3f ((k_high.pct_change(12)) / (1 + atr_nor… ✅ 1.947 1.138 -0.4196 0.000 0.512 0.261 ❌ REJECT scalar_score -0.4196 <= 0.0, sharpe_delta -14.6732 < -0.3, hypothesis test not confirmed
15 C8 gradient_boosting — — #7 k_loop_iter_15_5f90ab obv_ensemble_3 * (1 - price_position) /… ✅ 1.947 1.085 -0.4789 0.000 0.463 0.243 ❌ REJECT scalar_score -0.4789 <= 0.0, sharpe_delta -16.8215 < -0.3, hypothesis test not confirmed

📄 Report Markdown

# AUTOLOOP: zz_sylvain (15 iterations)

> **Phase**: Y4.7 Option B (DSL → Python code → FeatureSet candidate)
> **Target indicator**: zz_sylvain
> **Base feature_set_id**: 7
> **Claim**: (default) Propose a new k_* feature that improves risk-adjusted returns
> **Objective mode**: scalarize
> **Metrics**: ['profit_factor', 'sharpe_ratio', 'win_rate', 'max_drawdown', 'test_accuracy']
> **Total duration**: 502.03s
> **Total accepted**: 0
> **Total rejected**: 15

## Iterations 詳情

### Iteration 1
- DSL: `k_high.pct_change(12) * (1 - price_position) / (1 + i_atr(k_high, k_low, k_close, 14))` (feature=k_loop_iter_1_646216)
- DSL valid: True
- FeatureSet candidate id: 1317
- baseline PF: 1.947 → modified PF: 1.487
- t_stat: 0.000, p_value: 0.702, cohens_d: 0.124
- scalar_score: -0.1508
- accepted: False, reason: scalar_score -0.1508 <= 0.0, sharpe_delta -5.0829 < -0.3, hypothesis test not confirmed

**Metrics summary:**
  - profit_factor: baseline=1.947, modified=1.487, diff=-0.460
  - sharpe_ratio: baseline=19.162, modified=14.079, diff=-5.083
  - win_rate: baseline=0.600, modified=0.552, diff=-0.048
  - max_drawdown: baseline=0.056, modified=0.138, diff=0.082
  - test_accuracy: baseline=0.992, modified=0.983, diff=-0.010

### Iteration 2
- DSL: `k_high.pct_change(12) * (1 + hl_range) * (1 - dist_to_low) / (1 + atr_norm)` (feature=k_iter2_k_high_pct_change_hl_range_dist_to_low)
- DSL valid: False
- FeatureSet candidate id: None
- baseline PF: 0.000 → modified PF: 0.000
- t_stat: 0.000, p_value: 1.000, cohens_d: 0.000
- scalar_score: 0.0000
- accepted: False, reason: quality_gate: C8 leakage: ['dist_to_low']

### Iteration 3
- DSL: `obv_ensemble_3 * (1 - price_position) / (1 + atr_norm * 10)` (feature=k_iter3_price_position_atr_norm)
- DSL valid: False
- FeatureSet candidate id: None
- baseline PF: 0.000 → modified PF: 0.000
- t_stat: 0.000, p_value: 1.000, cohens_d: 0.000
- scalar_score: 0.0000
- accepted: False, reason: quality_gate: canonical duplicate: obv_ensemble_3 * (1 - price_position) / (1 + atr_norm * 10)

### Iteration 4
- DSL: `k_high.pct_change(12) * (1 + hl_range) * (1 - price_position) / (1 + atr_norm)` (feature=k_iter4_k_high_pct_change_hl_range_price_position)
- DSL valid: False
- FeatureSet candidate id: None
- baseline PF: 0.000 → modified PF: 0.000
- t_stat: 0.000, p_value: 1.000, cohens_d: 0.000
- scalar_score: 0.0000
- accepted: False, reason: quality_gate: canonical duplicate: k_high.pct_change * (1 + hl_range) * (1 - price_position) / (1 + atr_norm)

### Iteration 5
- DSL: `k_momentum_pct_change / (1 + i_atr(k_high, k_low, k_close, 14)) * (1 - return_5)` (feature=k_loop_iter_5_b45423)
- DSL valid: True
- FeatureSet candidate id: 1318
- baseline PF: 1.947 → modified PF: 1.243
- t_stat: 0.000, p_value: 0.386, cohens_d: 0.344
- scalar_score: -0.3300
- accepted: False, reason: scalar_score -0.3300 <= 0.0, sharpe_delta -11.5169 < -0.3, hypothesis test not confirmed

**Metrics summary:**
  - profit_factor: baseline=1.947, modified=1.243, diff=-0.704
  - sharpe_ratio: baseline=19.162, modified=7.645, diff=-11.517
  - win_rate: baseline=0.600, modified=0.489, diff=-0.111
  - max_drawdown: baseline=0.056, modified=0.126, diff=0.070
  - test_accuracy: baseline=0.992, modified=0.979, diff=-0.014

### Iteration 6
- DSL: `o_div_amplitude_12 * k_high.pct_change(12) / (1 + atr_norm * 10)` (feature=k_loop_iter_6_d72047)
- DSL valid: True
- FeatureSet candidate id: 1319
- baseline PF: 1.947 → modified PF: 1.138
- t_stat: 0.000, p_value: 0.512, cohens_d: 0.261
- scalar_score: -0.4196
- accepted: False, reason: scalar_score -0.4196 <= 0.0, sharpe_delta -14.6732 < -0.3, hypothesis test not confirmed

**Metrics summary:**
  - profit_factor: baseline=1.947, modified=1.138, diff=-0.810
  - sharpe_ratio: baseline=19.162, modified=4.489, diff=-14.673
  - win_rate: baseline=0.600, modified=0.466, diff=-0.134
  - max_drawdown: baseline=0.056, modified=0.166, diff=0.110
  - test_accuracy: baseline=0.992, modified=0.981, diff=-0.012

### Iteration 7
- DSL: `obv_ensemble_3 * k_high.pct_change(12) / (1 + atr_norm * 10)` (feature=k_loop_iter_7_e0bda4)
- DSL valid: True
- FeatureSet candidate id: 1320
- baseline PF: 1.947 → modified PF: 1.138
- t_stat: 0.000, p_value: 0.512, cohens_d: 0.261
- scalar_score: -0.4196
- accepted: False, reason: scalar_score -0.4196 <= 0.0, sharpe_delta -14.6732 < -0.3, hypothesis test not confirmed

**Metrics summary:**
  - profit_factor: baseline=1.947, modified=1.138, diff=-0.810
  - sharpe_ratio: baseline=19.162, modified=4.489, diff=-14.673
  - win_rate: baseline=0.600, modified=0.466, diff=-0.134
  - max_drawdown: baseline=0.056, modified=0.166, diff=0.110
  - test_accuracy: baseline=0.992, modified=0.981, diff=-0.012

### Iteration 8
- DSL: `obv_rebased.pct_change(12) * (1 - price_position) / (1 + atr_norm)` (feature=k_iter8_pct_change_price_position_atr_norm)
- DSL valid: False
- FeatureSet candidate id: None
- baseline PF: 0.000 → modified PF: 0.000
- t_stat: 0.000, p_value: 1.000, cohens_d: 0.000
- scalar_score: 0.0000
- accepted: False, reason: safe_eval DSL produced inf values; likely division by zero

### Iteration 9
- DSL: `i_rsi(k_close, 14) * (1 - price_position) * (1 + vol_ratio)` (feature=k_iter9_i_rsi_k_close_price_position_vol_ratio)
- DSL valid: False
- FeatureSet candidate id: None
- baseline PF: 0.000 → modified PF: 0.000
- t_stat: 0.000, p_value: 1.000, cohens_d: 0.000
- scalar_score: 0.0000
- accepted: False, reason: quality_gate: NaN ratio 1.000 exceeds 0.3

### Iteration 10
- DSL: `k_high.pct_change(12) / (1 + atr_norm) * (1 - price_position) * vol_ratio` (feature=k_loop_iter_10_5e3f44)
- DSL valid: True
- FeatureSet candidate id: 1321
- baseline PF: 1.947 → modified PF: 1.138
- t_stat: 0.000, p_value: 0.512, cohens_d: 0.261
- scalar_score: -0.4196
- accepted: False, reason: scalar_score -0.4196 <= 0.0, sharpe_delta -14.6732 < -0.3, hypothesis test not confirmed

**Metrics summary:**
  - profit_factor: baseline=1.947, modified=1.138, diff=-0.810
  - sharpe_ratio: baseline=19.162, modified=4.489, diff=-14.673
  - win_rate: baseline=0.600, modified=0.466, diff=-0.134
  - max_drawdown: baseline=0.056, modified=0.166, diff=0.110
  - test_accuracy: baseline=0.992, modified=0.981, diff=-0.012

### Iteration 11
- DSL: `obv_ensemble_3 * (1 - price_position) / (1 + atr_norm) * (1 + vol_ratio)` (feature=k_loop_iter_11_bdf5db)
- DSL valid: True
- FeatureSet candidate id: 1322
- baseline PF: 1.947 → modified PF: 1.085
- t_stat: 0.000, p_value: 0.463, cohens_d: 0.243
- scalar_score: -0.4789
- accepted: False, reason: scalar_score -0.4789 <= 0.0, sharpe_delta -16.8215 < -0.3, hypothesis test not confirmed

**Metrics summary:**
  - profit_factor: baseline=1.947, modified=1.085, diff=-0.862
  - sharpe_ratio: baseline=19.162, modified=2.341, diff=-16.821
  - win_rate: baseline=0.600, modified=0.500, diff=-0.100
  - max_drawdown: baseline=0.056, modified=0.187, diff=0.131
  - test_accuracy: baseline=0.992, modified=0.992, diff=-0.000

### Iteration 12
- DSL: `(k_high.pct_change(12) - i_rsi(k_close, 14).pct_change(5)) / (1 + atr_norm)` (feature=k_iter12_k_high_pct_change_i_rsi_k_close)
- DSL valid: False
- FeatureSet candidate id: None
- baseline PF: 0.000 → modified PF: 0.000
- t_stat: 0.000, p_value: 1.000, cohens_d: 0.000
- scalar_score: 0.0000
- accepted: False, reason: quality_gate: NaN ratio 1.000 exceeds 0.3

### Iteration 13
- DSL: `i_macd(k_close, 12, 26, 9) * (1 - price_position) / (1 + i_atr(k_high, k_low, k_close, 14) / k_close)` (feature=k_loop_iter_13_657217)
- DSL valid: True
- FeatureSet candidate id: 1323
- baseline PF: 1.947 → modified PF: 1.784
- t_stat: 0.000, p_value: 0.212, cohens_d: 0.534
- scalar_score: -0.4560
- accepted: False, reason: scalar_score -0.4560 <= 0.0, sharpe_delta -2.5358 < -0.3, hypothesis test not confirmed

**Metrics summary:**
  - profit_factor: baseline=1.947, modified=1.784, diff=-0.163
  - sharpe_ratio: baseline=19.162, modified=16.627, diff=-2.536
  - win_rate: baseline=0.600, modified=0.531, diff=-0.069
  - max_drawdown: baseline=0.056, modified=0.056, diff=0.000
  - test_accuracy: baseline=0.992, modified=0.992, diff=-0.000

### Iteration 14
- DSL: `((k_high.pct_change(12)) / (1 + atr_norm)) * (1 - price_position) * vol_ratio` (feature=k_loop_iter_14_28fa3f)
- DSL valid: True
- FeatureSet candidate id: 1324
- baseline PF: 1.947 → modified PF: 1.138
- t_stat: 0.000, p_value: 0.512, cohens_d: 0.261
- scalar_score: -0.4196
- accepted: False, reason: scalar_score -0.4196 <= 0.0, sharpe_delta -14.6732 < -0.3, hypothesis test not confirmed

**Metrics summary:**
  - profit_factor: baseline=1.947, modified=1.138, diff=-0.810
  - sharpe_ratio: baseline=19.162, modified=4.489, diff=-14.673
  - win_rate: baseline=0.600, modified=0.466, diff=-0.134
  - max_drawdown: baseline=0.056, modified=0.166, diff=0.110
  - test_accuracy: baseline=0.992, modified=0.981, diff=-0.012

### Iteration 15
- DSL: `obv_ensemble_3 * (1 - price_position) / (1 + atr_norm * 10) * vol_ratio` (feature=k_loop_iter_15_5f90ab)
- DSL valid: True
- FeatureSet candidate id: 1325
- baseline PF: 1.947 → modified PF: 1.085
- t_stat: 0.000, p_value: 0.463, cohens_d: 0.243
- scalar_score: -0.4789
- accepted: False, reason: scalar_score -0.4789 <= 0.0, sharpe_delta -16.8215 < -0.3, hypothesis test not confirmed

**Metrics summary:**
  - profit_factor: baseline=1.947, modified=1.085, diff=-0.862
  - sharpe_ratio: baseline=19.162, modified=2.341, diff=-16.821
  - win_rate: baseline=0.600, modified=0.500, diff=-0.100
  - max_drawdown: baseline=0.056, modified=0.187, diff=0.131
  - test_accuracy: baseline=0.992, modified=0.992, diff=-0.000

📊 Multi-Objective Metrics

Iteration 1: k_loop_iter_1_646216

Y Label: C8 | Parent FS: #7

Objective mode: scalarize

Scalar score: -0.1508

MetricBaselineModifiedDiff
win_rate 0.600 0.552 -0.048
max_drawdown 0.056 0.138 0.082
sharpe_ratio 19.162 14.079 -5.083
profit_factor 1.947 1.487 -0.460
test_accuracy 0.992 0.983 -0.010

Iteration 2: k_iter2_k_high_pct_change_hl_range_dist_to_low

Y Label: C8 | Parent FS: #7

Objective mode: single

Scalar score: 0.0000

Iteration 3: k_iter3_price_position_atr_norm

Y Label: C8 | Parent FS: #7

Objective mode: single

Scalar score: 0.0000

Iteration 4: k_iter4_k_high_pct_change_hl_range_price_position

Y Label: C8 | Parent FS: #7

Objective mode: single

Scalar score: 0.0000

Iteration 5: k_loop_iter_5_b45423

Y Label: C8 | Parent FS: #7

Objective mode: scalarize

Scalar score: -0.3300

MetricBaselineModifiedDiff
win_rate 0.600 0.489 -0.111
max_drawdown 0.056 0.126 0.070
sharpe_ratio 19.162 7.645 -11.517
profit_factor 1.947 1.243 -0.704
test_accuracy 0.992 0.979 -0.014

Iteration 6: k_loop_iter_6_d72047

Y Label: C8 | Parent FS: #7

Objective mode: scalarize

Scalar score: -0.4196

MetricBaselineModifiedDiff
win_rate 0.600 0.466 -0.134
max_drawdown 0.056 0.166 0.110
sharpe_ratio 19.162 4.489 -14.673
profit_factor 1.947 1.138 -0.810
test_accuracy 0.992 0.981 -0.012

Iteration 7: k_loop_iter_7_e0bda4

Y Label: C8 | Parent FS: #7

Objective mode: scalarize

Scalar score: -0.4196

MetricBaselineModifiedDiff
win_rate 0.600 0.466 -0.134
max_drawdown 0.056 0.166 0.110
sharpe_ratio 19.162 4.489 -14.673
profit_factor 1.947 1.138 -0.810
test_accuracy 0.992 0.981 -0.012

Iteration 8: k_iter8_pct_change_price_position_atr_norm

Y Label: C8 | Parent FS: #7

Objective mode: single

Scalar score: 0.0000

Iteration 9: k_iter9_i_rsi_k_close_price_position_vol_ratio

Y Label: C8 | Parent FS: #7

Objective mode: single

Scalar score: 0.0000

Iteration 10: k_loop_iter_10_5e3f44

Y Label: C8 | Parent FS: #7

Objective mode: scalarize

Scalar score: -0.4196

MetricBaselineModifiedDiff
win_rate 0.600 0.466 -0.134
max_drawdown 0.056 0.166 0.110
sharpe_ratio 19.162 4.489 -14.673
profit_factor 1.947 1.138 -0.810
test_accuracy 0.992 0.981 -0.012

Iteration 11: k_loop_iter_11_bdf5db

Y Label: C8 | Parent FS: #7

Objective mode: scalarize

Scalar score: -0.4789

MetricBaselineModifiedDiff
win_rate 0.600 0.500 -0.100
max_drawdown 0.056 0.187 0.131
sharpe_ratio 19.162 2.341 -16.821
profit_factor 1.947 1.085 -0.862
test_accuracy 0.992 0.992 0.000

Iteration 12: k_iter12_k_high_pct_change_i_rsi_k_close

Y Label: C8 | Parent FS: #7

Objective mode: single

Scalar score: 0.0000

Iteration 13: k_loop_iter_13_657217

Y Label: C8 | Parent FS: #7

Objective mode: scalarize

Scalar score: -0.4560

MetricBaselineModifiedDiff
win_rate 0.600 0.531 -0.069
max_drawdown 0.056 0.056 0.000
sharpe_ratio 19.162 16.627 -2.536
profit_factor 1.947 1.784 -0.163
test_accuracy 0.992 0.992 0.000

Iteration 14: k_loop_iter_14_28fa3f

Y Label: C8 | Parent FS: #7

Objective mode: scalarize

Scalar score: -0.4196

MetricBaselineModifiedDiff
win_rate 0.600 0.466 -0.134
max_drawdown 0.056 0.166 0.110
sharpe_ratio 19.162 4.489 -14.673
profit_factor 1.947 1.138 -0.810
test_accuracy 0.992 0.981 -0.012

Iteration 15: k_loop_iter_15_5f90ab

Y Label: C8 | Parent FS: #7

Objective mode: scalarize

Scalar score: -0.4789

MetricBaselineModifiedDiff
win_rate 0.600 0.500 -0.100
max_drawdown 0.056 0.187 0.131
sharpe_ratio 19.162 2.341 -16.821
profit_factor 1.947 1.085 -0.862
test_accuracy 0.992 0.992 0.000

📁 Offline Report

Markdown backup: reports/autoloop/zz_sylvain/20260726_192615.md