跳到主要內容

Feature Iteration Run #562: zz_sylvain

Status: completed | Started: 2026-07-18 03:02:26 | Ended: 2026-07-18 03:03:52

📊 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_09d107 i_sma(k_close, 30) - i_sma(k_close, 5) ✅ 1.286 1.276 -0.0787 0.000 1.000 0.000 ❌ REJECT p=1.000 ≥ 0.05, cohens_d=0.000 ≤ 0.3
2 — gradient_boosting — — #7 k_loop_iter_2_f81363 i_hma(k_close, 20) - i_ema(k_close, 50) ✅ 1.286 1.257 -0.1842 0.000 1.000 0.000 ❌ REJECT p=1.000 ≥ 0.05, cohens_d=0.000 ≤ 0.3

📄 Report Markdown

# AUTOLOOP: zz_sylvain (2 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**: 85.93s
> **Total accepted**: 0
> **Total rejected**: 2

## Iterations 詳情

### Iteration 1
- DSL: `i_sma(k_close, 30) - i_sma(k_close, 5)` (feature=k_loop_iter_1_09d107)
- DSL valid: True
- FeatureSet candidate id: 654
- baseline PF: 1.286 → modified PF: 1.276
- t_stat: 0.000, p_value: 1.000, cohens_d: 0.000
- scalar_score: -0.0787
- accepted: False, reason: p=1.000 ≥ 0.05, cohens_d=0.000 ≤ 0.3

**Metrics summary:**
  - profit_factor: baseline=1.286, modified=1.276, diff=-0.009
  - sharpe_ratio: baseline=7.879, modified=7.584, diff=-0.295
  - win_rate: baseline=0.553, modified=0.542, diff=-0.012
  - max_drawdown: baseline=0.075, modified=0.077, diff=0.002
  - test_accuracy: baseline=0.986, modified=0.986, diff=-0.000

### Iteration 2
- DSL: `i_hma(k_close, 20) - i_ema(k_close, 50)` (feature=k_loop_iter_2_f81363)
- DSL valid: True
- FeatureSet candidate id: 655
- baseline PF: 1.286 → modified PF: 1.257
- t_stat: 0.000, p_value: 1.000, cohens_d: 0.000
- scalar_score: -0.1842
- accepted: False, reason: p=1.000 ≥ 0.05, cohens_d=0.000 ≤ 0.3

**Metrics summary:**
  - profit_factor: baseline=1.286, modified=1.257, diff=-0.029
  - sharpe_ratio: baseline=7.879, modified=7.194, diff=-0.685
  - win_rate: baseline=0.553, modified=0.532, diff=-0.021
  - max_drawdown: baseline=0.075, modified=0.075, diff=0.000
  - test_accuracy: baseline=0.986, modified=0.986, diff=0.000

📊 Multi-Objective Metrics

Iteration 1: k_loop_iter_1_09d107

Y Label: — | Parent FS: #7

Objective mode: scalarize

Scalar score: -0.0787

MetricBaselineModifiedDiff
win_rate 0.553 0.542 -0.012
max_drawdown 0.075 0.077 0.002
sharpe_ratio 7.879 7.584 -0.295
profit_factor 1.286 1.276 -0.009
test_accuracy 0.986 0.986 0.000

Iteration 2: k_loop_iter_2_f81363

Y Label: — | Parent FS: #7

Objective mode: scalarize

Scalar score: -0.1842

MetricBaselineModifiedDiff
win_rate 0.553 0.532 -0.021
max_drawdown 0.075 0.075 0.000
sharpe_ratio 7.879 7.194 -0.685
profit_factor 1.286 1.257 -0.029
test_accuracy 0.986 0.986 0.000

📁 Offline Report

Markdown backup: reports/autoloop/zz_sylvain/20260718_110352.md