跳到主要內容

Feature Iteration Run #550: zz_sylvain

Status: completed | Started: 2026-07-18 02:52:03 | Ended: 2026-07-18 02:53:23

⭐ Best Accepted Iteration

Iteration 1: k_high.pct_change(12)

baseline PF: 1.286 → modified PF: 2.113 | Cohen's d: 0.000 | p-value: 1.000

📊 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_75605d k_high.pct_change(12) ✅ 1.286 2.113 3.7086 0.000 1.000 0.000 ✅ ACCEPT accepted
2 — gradient_boosting — — #7 k_loop_iter_2_0d3edb k_close.rolling(20).mean() ✅ 1.286 1.424 0.8055 0.000 1.000 0.000 ✅ ACCEPT accepted

📄 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**: 80.31s
> **Total accepted**: 2
> **Total rejected**: 0

## Iterations 詳情

### Iteration 1
- DSL: `k_high.pct_change(12)` (feature=k_loop_iter_1_75605d)
- DSL valid: True
- FeatureSet candidate id: 634
- baseline PF: 1.286 → modified PF: 2.113
- t_stat: 0.000, p_value: 1.000, cohens_d: 0.000
- scalar_score: 3.7086
- accepted: True, reason: accepted

**Metrics summary:**
  - profit_factor: baseline=1.286, modified=2.113, diff=0.827
  - sharpe_ratio: baseline=7.879, modified=21.700, diff=13.821
  - win_rate: baseline=0.553, modified=0.596, diff=0.043
  - max_drawdown: baseline=0.075, modified=0.051, diff=-0.023
  - test_accuracy: baseline=0.986, modified=0.986, diff=0.000

### Iteration 2
- DSL: `k_close.rolling(20).mean()` (feature=k_loop_iter_2_0d3edb)
- DSL valid: True
- FeatureSet candidate id: 635
- baseline PF: 1.286 → modified PF: 1.424
- t_stat: 0.000, p_value: 1.000, cohens_d: 0.000
- scalar_score: 0.8055
- accepted: True, reason: accepted

**Metrics summary:**
  - profit_factor: baseline=1.286, modified=1.424, diff=0.138
  - sharpe_ratio: baseline=7.879, modified=10.933, diff=3.054
  - win_rate: baseline=0.553, modified=0.574, diff=0.021
  - max_drawdown: baseline=0.075, modified=0.051, diff=-0.023
  - test_accuracy: baseline=0.986, modified=0.986, diff=0.000

📊 Multi-Objective Metrics

Iteration 1: k_loop_iter_1_75605d

Y Label: — | Parent FS: #7

Objective mode: scalarize

Scalar score: 3.7086

MetricBaselineModifiedDiff
win_rate 0.553 0.596 0.043
max_drawdown 0.075 0.051 -0.023
sharpe_ratio 7.879 21.700 13.821
profit_factor 1.286 2.113 0.827
test_accuracy 0.986 0.986 0.000

Iteration 2: k_loop_iter_2_0d3edb

Y Label: — | Parent FS: #7

Objective mode: scalarize

Scalar score: 0.8055

MetricBaselineModifiedDiff
win_rate 0.553 0.574 0.021
max_drawdown 0.075 0.051 -0.023
sharpe_ratio 7.879 10.933 3.054
profit_factor 1.286 1.424 0.138
test_accuracy 0.986 0.986 0.000

📁 Offline Report

Markdown backup: reports/autoloop/zz_sylvain/20260718_105323.md