跳到主要內容

Feature Iteration Run #489: zz_sylvain

Status: completed | Started: 2026-07-17 15:47:53 | Ended: 2026-07-17 15:49:05

📊 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_75605d k_high.pct_change(12) ✅ 1.286 1.062 -1.6362 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) 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**: 72.27s
> **Total accepted**: 0
> **Total rejected**: 1

## Iterations 詳情

### Iteration 1
- DSL: `k_high.pct_change(12)` (feature=k_loop_iter_1_75605d)
- DSL valid: True
- FeatureSet candidate id: 532
- baseline PF: 1.286 → modified PF: 1.062
- t_stat: 0.000, p_value: 1.000, cohens_d: 0.000
- scalar_score: -1.6362
- accepted: False, reason: p=1.000 ≥ 0.05, cohens_d=0.000 ≤ 0.3

**Metrics summary:**
  - profit_factor: baseline=1.286, modified=1.062, diff=-0.223
  - sharpe_ratio: baseline=7.879, modified=1.675, diff=-6.204
  - win_rate: baseline=0.553, modified=0.438, diff=-0.115
  - max_drawdown: baseline=0.075, modified=0.118, diff=0.043
  - test_accuracy: baseline=0.986, modified=0.970, diff=-0.016

📊 Multi-Objective Metrics

Iteration 1: k_loop_iter_1_75605d

Y Label: — | Parent FS: #—

Objective mode: scalarize

Scalar score: -1.6362

MetricBaselineModifiedDiff
win_rate 0.553 0.438 -0.115
max_drawdown 0.075 0.118 0.043
sharpe_ratio 7.879 1.675 -6.204
profit_factor 1.286 1.062 -0.223
test_accuracy 0.986 0.970 -0.016

📁 Offline Report

Markdown backup: reports/autoloop/zz_sylvain/20260717_234905.md