跳到主要內容

Feature Iteration Run #850: zz_sylvain

Status: completed | Started: 2026-07-24 03:57:38 | Ended: 2026-07-24 04:00:47

⭐ Best Accepted Iteration

Iteration 3: k_high.pct_change(12) * (1 - dist_to_high) / (1 + atr_norm)…

baseline PF: 1.947 → modified PF: 2.481 | Cohen's d: 0.281 | p-value: 0.046

📊 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_1cbb61 k_high.pct_change(12) * o_div_amplitude… ✅ 1.947 1.138 -0.3923 0.000 0.512 0.261 ❌ REJECT min_p=0.512 ≥ 0.05
2 C8 gradient_boosting — — #7 k_loop_iter_2_615d19 k_high.pct_change(12) * (1 - price_posi… ✅ 1.947 1.138 -0.3923 0.000 0.512 0.261 ❌ REJECT min_p=0.512 ≥ 0.05
3 C8 gradient_boosting — — #7 k_loop_iter_3_6934d9 k_high.pct_change(12) * (1 - dist_to_hi… ✅ 1.947 2.481 1.3042 0.000 0.046 0.281 ✅ ACCEPT accepted
4 C8 gradient_boosting — — #1200 k_loop_iter_4_c0236b i_rsi(k_close, 14) * (1 - dist_to_high)… ✅ 1.947 1.261 -0.3510 0.000 0.274 0.364 ❌ REJECT min_p=0.274 ≥ 0.05

📄 Report Markdown

# AUTOLOOP: zz_sylvain (4 iterations)

> **Phase**: Y4.7 Option B (DSL → Python code → FeatureSet candidate)
> **Target indicator**: zz_sylvain
> **Base feature_set_id**: 1200
> **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**: 189.27s
> **Total accepted**: 1
> **Total rejected**: 3

## Iterations 詳情

### Iteration 1
- DSL: `k_high.pct_change(12) * o_div_amplitude_12 / (1 + atr_norm)` (feature=k_loop_iter_1_1cbb61)
- DSL valid: True
- FeatureSet candidate id: 1198
- baseline PF: 1.947 → modified PF: 1.138
- t_stat: 0.000, p_value: 0.512, cohens_d: 0.261
- scalar_score: -0.3923
- accepted: False, reason: min_p=0.512 ≥ 0.05

**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 2
- DSL: `k_high.pct_change(12) * (1 - price_position) / (1 + atr_norm) * o_div_amplitude_12` (feature=k_loop_iter_2_615d19)
- DSL valid: True
- FeatureSet candidate id: 1199
- baseline PF: 1.947 → modified PF: 1.138
- t_stat: 0.000, p_value: 0.512, cohens_d: 0.261
- scalar_score: -0.3923
- accepted: False, reason: min_p=0.512 ≥ 0.05

**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 3
- DSL: `k_high.pct_change(12) * (1 - dist_to_high) / (1 + atr_norm) * i_rsi(k_close, 14)` (feature=k_loop_iter_3_6934d9)
- DSL valid: True
- FeatureSet candidate id: 1200
- baseline PF: 1.947 → modified PF: 2.481
- t_stat: 0.000, p_value: 0.046, cohens_d: 0.281
- scalar_score: 1.3042
- accepted: True, reason: accepted

**Metrics summary:**
  - profit_factor: baseline=1.947, modified=2.481, diff=0.534
  - sharpe_ratio: baseline=19.162, modified=24.452, diff=5.290
  - win_rate: baseline=0.600, modified=0.567, 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 4
- DSL: `i_rsi(k_close, 14) * (1 - dist_to_high) / (1 + atr_norm) * k_high.pct_change(12)` (feature=k_loop_iter_4_c0236b)
- DSL valid: True
- FeatureSet candidate id: 1201
- baseline PF: 1.947 → modified PF: 1.261
- t_stat: 0.000, p_value: 0.274, cohens_d: 0.364
- scalar_score: -0.3510
- accepted: False, reason: min_p=0.274 ≥ 0.05

**Metrics summary:**
  - profit_factor: baseline=1.947, modified=1.261, diff=-0.687
  - sharpe_ratio: baseline=19.162, modified=7.116, diff=-12.046
  - win_rate: baseline=0.600, modified=0.430, diff=-0.170
  - max_drawdown: baseline=0.056, modified=0.097, diff=0.041
  - test_accuracy: baseline=0.992, modified=0.990, diff=-0.002

📊 Multi-Objective Metrics

Iteration 1: k_loop_iter_1_1cbb61

Y Label: C8 | Parent FS: #7

Objective mode: scalarize

Scalar score: -0.3923

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 2: k_loop_iter_2_615d19

Y Label: C8 | Parent FS: #7

Objective mode: scalarize

Scalar score: -0.3923

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 3: k_loop_iter_3_6934d9

Y Label: C8 | Parent FS: #7

Objective mode: scalarize

Scalar score: 1.3042

MetricBaselineModifiedDiff
win_rate 0.600 0.567 -0.033
max_drawdown 0.056 0.056 0.000
sharpe_ratio 19.162 24.452 5.290
profit_factor 1.947 2.481 0.534
test_accuracy 0.992 0.992 0.000

Iteration 4: k_loop_iter_4_c0236b

Y Label: C8 | Parent FS: #1200

Objective mode: scalarize

Scalar score: -0.3510

MetricBaselineModifiedDiff
win_rate 0.600 0.430 -0.170
max_drawdown 0.056 0.097 0.041
sharpe_ratio 19.162 7.116 -12.046
profit_factor 1.947 1.261 -0.687
test_accuracy 0.992 0.990 -0.002

📁 Offline Report

Markdown backup: reports/autoloop/zz_sylvain/20260724_120047.md