跳到主要內容

Feature Iteration Run #333: zz_sylvain

Status: completed | Started: 2026-07-16 11:56:41 | Ended: 2026-07-16 12:04:23

📊 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 — — — K_loop_iter_1_563283 k_high.pct_change(12) ✅ 1.254 1.189 -0.4435 0.000 1.000 0.000 ❌ REJECT p=1.000 ≥ 0.05, cohens_d=0.000 ≤ 0.3

📄 Report Markdown

# AUTOLOOP: zz_sylvain (1 iterations)

> **Phase**: Y4.7 Option B (DSL → Python code → FeatureSet candidate)
> **Target indicator**: zz_sylvain
> **Base feature_set_id**: 7
> **Claim**: (default) Adding k_high_pct_change_12 improves Sharpe by 10%
> **Objective mode**: scalarize
> **Metrics**: ['profit_factor', 'sharpe_ratio', 'win_rate', 'max_drawdown', 'test_accuracy']
> **Total duration**: 461.95s
> **Total accepted**: 0
> **Total rejected**: 1

## Iterations 詳情

### Iteration 1
- DSL: `k_high.pct_change(12)` (feature=K_loop_iter_1_563283)
- DSL valid: True
- FeatureSet candidate id: 296
- baseline PF: 1.254 → modified PF: 1.189
- t_stat: 0.000, p_value: 1.000, cohens_d: 0.000
- scalar_score: -0.4435
- accepted: False, reason: p=1.000 ≥ 0.05, cohens_d=0.000 ≤ 0.3

**Metrics summary:**
  - profit_factor: baseline=1.254, modified=1.189, diff=-0.064
  - sharpe_ratio: baseline=7.362, modified=5.699, diff=-1.663
  - win_rate: baseline=0.436, modified=0.415, diff=-0.021
  - max_drawdown: baseline=0.084, modified=0.055, diff=-0.029
  - test_accuracy: baseline=0.972, modified=0.974, diff=0.001

📊 Multi-Objective Metrics

Iteration 1: K_loop_iter_1_563283

Y Label: — | Parent FS: #—

Objective mode: scalarize

Scalar score: -0.4435

MetricBaselineModifiedDiff
win_rate 0.436 0.415 -0.021
max_drawdown 0.084 0.055 -0.029
sharpe_ratio 7.362 5.699 -1.663
profit_factor 1.254 1.189 -0.064
test_accuracy 0.972 0.974 0.001

📁 Offline Report

Markdown backup: reports/autoloop/zz_sylvain/20260716_200423.md