跳到主要內容

Feature Iteration Run #836: zz_sylvain

Status: completed | Started: 2026-07-21 08:25:51 | Ended: 2026-07-21 08:30:42

⭐ Best Accepted Iteration

Iteration 8: k_high.pct_change(12) * (1 + hl_range) * (1 - price_positio…

baseline PF: 1.947 → modified PF: 2.737 | Cohen's d: 0.471 | p-value: 0.045

📊 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 — gradient_boosting — — #7 k_loop_iter_1_1b496e obv_ensemble_3 * (1 - dist_to_high) / (… ✅ 1.947 1.085 -0.4478 0.000 0.463 0.243 ❌ REJECT min_p=0.463 ≥ 0.05
2 — gradient_boosting — — #7 k_loop_iter_2_4ec712 k_high.pct_change(12) / (1 + atr_norm) … ✅ 1.947 2.466 0.6193 0.000 0.296 0.211 ✅ ACCEPT accepted
3 — gradient_boosting — — #7 k_iter3_k_high_pct_change_atr_norm_price_position (k_high.pct_change(12) / (1 + atr_norm)… ❌ 0.000 0.000 0.0000 0.000 1.000 0.000 ❌ REJECT safe_eval DSL produced inf values; likely division by zero
4 — gradient_boosting — — #7 k_loop_iter_4_713f78 k_high.pct_change(12) * (1 + hl_range) … ✅ 1.947 2.466 1.3886 0.000 0.012 0.388 ✅ ACCEPT accepted
5 — gradient_boosting — — #7 k_loop_iter_5_988ae3 k_high.pct_change(12) * (1 + hl_range) … ✅ 1.947 2.401 0.9424 0.000 0.021 0.388 ✅ ACCEPT accepted
6 — gradient_boosting — — #7 k_loop_iter_6_5ef6e4 k_high.pct_change(12) * (1 + hl_range) … ✅ 1.947 2.466 1.4338 0.000 0.012 0.325 ✅ ACCEPT accepted
7 — gradient_boosting — — #7 k_loop_iter_7_e208da k_high.pct_change(12) * (1 + hl_range) … ✅ 1.947 2.244 1.1437 0.000 0.000 0.463 ✅ ACCEPT accepted
8 — gradient_boosting — — #7 k_loop_iter_8_7abbe1 k_high.pct_change(12) * (1 + hl_range) … ✅ 1.947 2.737 2.1588 0.000 0.045 0.471 ✅ ACCEPT accepted

📄 Report Markdown

# AUTOLOOP: zz_sylvain (8 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**: 290.38s
> **Total accepted**: 6
> **Total rejected**: 2

## Iterations 詳情

### Iteration 1
- DSL: `obv_ensemble_3 * (1 - dist_to_high) / (1 + atr_norm)` (feature=k_loop_iter_1_1b496e)
- DSL valid: True
- FeatureSet candidate id: 1166
- baseline PF: 1.947 → modified PF: 1.085
- t_stat: 0.000, p_value: 0.463, cohens_d: 0.243
- scalar_score: -0.4478
- accepted: False, reason: min_p=0.463 ≥ 0.05

**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 2
- DSL: `k_high.pct_change(12) / (1 + atr_norm) * (1 - price_position) * (1 - dist_to_high) * (1 + hl_range)` (feature=k_loop_iter_2_4ec712)
- DSL valid: True
- FeatureSet candidate id: 1167
- baseline PF: 1.947 → modified PF: 2.466
- t_stat: 0.000, p_value: 0.296, cohens_d: 0.211
- scalar_score: 0.6193
- accepted: True, reason: accepted

**Metrics summary:**
  - profit_factor: baseline=1.947, modified=2.466, diff=0.519
  - sharpe_ratio: baseline=19.162, modified=24.727, diff=5.565
  - win_rate: baseline=0.600, modified=0.636, diff=0.036
  - max_drawdown: baseline=0.056, modified=0.050, diff=-0.006
  - test_accuracy: baseline=0.992, modified=0.992, diff=-0.000

### Iteration 3
- DSL: `(k_high.pct_change(12) / (1 + atr_norm)) * (1 - price_position) * (1 - dist_to_high) * obv_rebased.pct_change(12)` (feature=k_iter3_k_high_pct_change_atr_norm_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: safe_eval DSL produced inf values; likely division by zero

### Iteration 4
- DSL: `k_high.pct_change(12) * (1 + hl_range) * (1 - price_position) * (1 - dist_to_low) / (1 + atr_norm)` (feature=k_loop_iter_4_713f78)
- DSL valid: True
- FeatureSet candidate id: 1168
- baseline PF: 1.947 → modified PF: 2.466
- t_stat: 0.000, p_value: 0.012, cohens_d: 0.388
- scalar_score: 1.3886
- accepted: True, reason: accepted

**Metrics summary:**
  - profit_factor: baseline=1.947, modified=2.466, diff=0.519
  - sharpe_ratio: baseline=19.162, modified=24.727, diff=5.565
  - win_rate: baseline=0.600, modified=0.636, diff=0.036
  - max_drawdown: baseline=0.056, modified=0.050, diff=-0.006
  - test_accuracy: baseline=0.992, modified=0.992, diff=-0.000

### Iteration 5
- DSL: `k_high.pct_change(12) * (1 + hl_range) * (1 - price_position) * (1 - dist_to_low) / (1 + atr_norm) * i_rsi(k_close, 14) / 100` (feature=k_loop_iter_5_988ae3)
- DSL valid: True
- FeatureSet candidate id: 1169
- baseline PF: 1.947 → modified PF: 2.401
- t_stat: 0.000, p_value: 0.021, cohens_d: 0.388
- scalar_score: 0.9424
- accepted: True, reason: accepted

**Metrics summary:**
  - profit_factor: baseline=1.947, modified=2.401, diff=0.453
  - sharpe_ratio: baseline=19.162, modified=23.405, diff=4.243
  - win_rate: baseline=0.600, modified=0.548, diff=-0.052
  - max_drawdown: baseline=0.056, modified=0.056, diff=0.000
  - test_accuracy: baseline=0.992, modified=0.992, diff=-0.001

### Iteration 6
- DSL: `k_high.pct_change(12) * (1 + hl_range) * (1 - price_position) * (1 - dist_to_low) / (1 + atr_norm) * (k_momentum_pct_change - o_div_amplitude_12) / (k_momentum_pct_change + 1e-10)` (feature=k_loop_iter_6_5ef6e4)
- DSL valid: True
- FeatureSet candidate id: 1170
- baseline PF: 1.947 → modified PF: 2.466
- t_stat: 0.000, p_value: 0.012, cohens_d: 0.325
- scalar_score: 1.4338
- accepted: True, reason: accepted

**Metrics summary:**
  - profit_factor: baseline=1.947, modified=2.466, diff=0.519
  - sharpe_ratio: baseline=19.162, modified=24.727, diff=5.565
  - win_rate: baseline=0.600, modified=0.636, diff=0.036
  - max_drawdown: baseline=0.056, modified=0.050, diff=-0.006
  - test_accuracy: baseline=0.992, modified=0.992, diff=-0.000

### Iteration 7
- DSL: `k_high.pct_change(12) * (1 + hl_range) * (1 - price_position) * (1 - dist_to_low) / (1 + atr_norm) * i_macd(k_close, 12, 26, 9) / (k_close + 1e-10)` (feature=k_loop_iter_7_e208da)
- DSL valid: True
- FeatureSet candidate id: 1171
- baseline PF: 1.947 → modified PF: 2.244
- t_stat: 0.000, p_value: 0.000, cohens_d: 0.463
- scalar_score: 1.1437
- accepted: True, reason: accepted

**Metrics summary:**
  - profit_factor: baseline=1.947, modified=2.244, diff=0.297
  - sharpe_ratio: baseline=19.162, modified=23.357, diff=4.195
  - win_rate: baseline=0.600, modified=0.633, diff=0.033
  - max_drawdown: baseline=0.056, modified=0.056, diff=-0.000
  - test_accuracy: baseline=0.992, modified=0.992, diff=0.000

### Iteration 8
- DSL: `k_high.pct_change(12) * (1 + hl_range) * (1 - price_position) * (1 - dist_to_low) / (1 + atr_norm) * (i_ema(k_close, 20) - i_ema(k_close, 50)) / (k_close + 1e-10)` (feature=k_loop_iter_8_7abbe1)
- DSL valid: True
- FeatureSet candidate id: 1172
- baseline PF: 1.947 → modified PF: 2.737
- t_stat: 0.000, p_value: 0.045, cohens_d: 0.471
- scalar_score: 2.1588
- accepted: True, reason: accepted

**Metrics summary:**
  - profit_factor: baseline=1.947, modified=2.737, diff=0.789
  - sharpe_ratio: baseline=19.162, modified=27.830, diff=8.667
  - win_rate: baseline=0.600, modified=0.690, diff=0.090
  - max_drawdown: baseline=0.056, modified=0.042, diff=-0.014
  - test_accuracy: baseline=0.992, modified=0.992, diff=-0.000

📊 Multi-Objective Metrics

Iteration 1: k_loop_iter_1_1b496e

Y Label: — | Parent FS: #7

Objective mode: scalarize

Scalar score: -0.4478

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 2: k_loop_iter_2_4ec712

Y Label: — | Parent FS: #7

Objective mode: scalarize

Scalar score: 0.6193

MetricBaselineModifiedDiff
win_rate 0.600 0.636 0.036
max_drawdown 0.056 0.050 -0.006
sharpe_ratio 19.162 24.727 5.565
profit_factor 1.947 2.466 0.519
test_accuracy 0.992 0.992 0.000

Iteration 3: k_iter3_k_high_pct_change_atr_norm_price_position

Y Label: — | Parent FS: #7

Objective mode: single

Scalar score: 0.0000

Iteration 4: k_loop_iter_4_713f78

Y Label: — | Parent FS: #7

Objective mode: scalarize

Scalar score: 1.3886

MetricBaselineModifiedDiff
win_rate 0.600 0.636 0.036
max_drawdown 0.056 0.050 -0.006
sharpe_ratio 19.162 24.727 5.565
profit_factor 1.947 2.466 0.519
test_accuracy 0.992 0.992 0.000

Iteration 5: k_loop_iter_5_988ae3

Y Label: — | Parent FS: #7

Objective mode: scalarize

Scalar score: 0.9424

MetricBaselineModifiedDiff
win_rate 0.600 0.548 -0.052
max_drawdown 0.056 0.056 0.000
sharpe_ratio 19.162 23.405 4.243
profit_factor 1.947 2.401 0.453
test_accuracy 0.992 0.992 -0.001

Iteration 6: k_loop_iter_6_5ef6e4

Y Label: — | Parent FS: #7

Objective mode: scalarize

Scalar score: 1.4338

MetricBaselineModifiedDiff
win_rate 0.600 0.636 0.036
max_drawdown 0.056 0.050 -0.006
sharpe_ratio 19.162 24.727 5.565
profit_factor 1.947 2.466 0.519
test_accuracy 0.992 0.992 0.000

Iteration 7: k_loop_iter_7_e208da

Y Label: — | Parent FS: #7

Objective mode: scalarize

Scalar score: 1.1437

MetricBaselineModifiedDiff
win_rate 0.600 0.633 0.033
max_drawdown 0.056 0.056 0.000
sharpe_ratio 19.162 23.357 4.195
profit_factor 1.947 2.244 0.297
test_accuracy 0.992 0.992 0.000

Iteration 8: k_loop_iter_8_7abbe1

Y Label: — | Parent FS: #7

Objective mode: scalarize

Scalar score: 2.1588

MetricBaselineModifiedDiff
win_rate 0.600 0.690 0.090
max_drawdown 0.056 0.042 -0.014
sharpe_ratio 19.162 27.830 8.667
profit_factor 1.947 2.737 0.789
test_accuracy 0.992 0.992 0.000

📁 Offline Report

Markdown backup: reports/autoloop/zz_sylvain/20260721_163042.md