跳到主要內容

Feature Iteration Run #578: zz_sylvain

Status: completed | Started: 2026-07-18 03:56:10 | Ended: 2026-07-18 03:58:10

⭐ Best Accepted Iteration

Iteration 1: k_high.pct_change(12) - i_rsi(k_close, 14) / 100

baseline PF: 1.286 → modified PF: 1.499 | 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_03782b k_high.pct_change(12) - i_rsi(k_close, … ✅ 1.286 1.499 1.1713 0.000 1.000 0.000 ✅ ACCEPT accepted
2 — gradient_boosting — — #7 k_loop_iter_2_a4e04a i_boll(k_close, 20) - i_ema(k_close, 50) ✅ 1.286 1.286 0.0000 0.000 1.000 0.000 ❌ REJECT p=1.000 ≥ 0.05, cohens_d=0.000 ≤ 0.3
3 — gradient_boosting — — #7 k_loop_iter_3_53ceb1 k_high.pct_change(12) * vol_ratio - i_r… ✅ 1.286 1.604 1.7212 0.000 1.000 0.000 ✅ ACCEPT accepted

📄 Report Markdown

# AUTOLOOP: zz_sylvain (3 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**: 119.74s
> **Total accepted**: 2
> **Total rejected**: 1

## Iterations 詳情

### Iteration 1
- DSL: `k_high.pct_change(12) - i_rsi(k_close, 14) / 100` (feature=k_loop_iter_1_03782b)
- DSL valid: True
- FeatureSet candidate id: 686
- baseline PF: 1.286 → modified PF: 1.499
- t_stat: 0.000, p_value: 1.000, cohens_d: 0.000
- scalar_score: 1.1713
- accepted: True, reason: accepted

**Metrics summary:**
  - profit_factor: baseline=1.286, modified=1.499, diff=0.213
  - sharpe_ratio: baseline=7.879, modified=12.302, diff=4.423
  - win_rate: baseline=0.553, modified=0.566, diff=0.013
  - max_drawdown: baseline=0.075, modified=0.069, diff=-0.006
  - test_accuracy: baseline=0.986, modified=0.986, diff=-0.000

### Iteration 2
- DSL: `i_boll(k_close, 20) - i_ema(k_close, 50)` (feature=k_loop_iter_2_a4e04a)
- DSL valid: True
- FeatureSet candidate id: 687
- baseline PF: 1.286 → modified PF: 1.286
- t_stat: 0.000, p_value: 1.000, cohens_d: 0.000
- scalar_score: -0.0000
- accepted: False, reason: p=1.000 ≥ 0.05, cohens_d=0.000 ≤ 0.3

**Metrics summary:**
  - profit_factor: baseline=1.286, modified=1.286, diff=0.000
  - sharpe_ratio: baseline=7.879, modified=7.879, diff=-0.000
  - win_rate: baseline=0.553, modified=0.553, diff=0.000
  - max_drawdown: baseline=0.075, modified=0.075, diff=0.000
  - test_accuracy: baseline=0.986, modified=0.986, diff=0.000

### Iteration 3
- DSL: `k_high.pct_change(12) * vol_ratio - i_rsi(k_close, 14) / 100` (feature=k_loop_iter_3_53ceb1)
- DSL valid: True
- FeatureSet candidate id: 688
- baseline PF: 1.286 → modified PF: 1.604
- t_stat: 0.000, p_value: 1.000, cohens_d: 0.000
- scalar_score: 1.7212
- accepted: True, reason: accepted

**Metrics summary:**
  - profit_factor: baseline=1.286, modified=1.604, diff=0.318
  - sharpe_ratio: baseline=7.879, modified=14.382, diff=6.503
  - win_rate: baseline=0.553, modified=0.571, diff=0.018
  - 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_03782b

Y Label: — | Parent FS: #7

Objective mode: scalarize

Scalar score: 1.1713

MetricBaselineModifiedDiff
win_rate 0.553 0.566 0.013
max_drawdown 0.075 0.069 -0.006
sharpe_ratio 7.879 12.302 4.423
profit_factor 1.286 1.499 0.213
test_accuracy 0.986 0.986 0.000

Iteration 2: k_loop_iter_2_a4e04a

Y Label: — | Parent FS: #7

Objective mode: scalarize

Scalar score: 0.0000

MetricBaselineModifiedDiff
win_rate 0.553 0.553 0.000
max_drawdown 0.075 0.075 0.000
sharpe_ratio 7.879 7.879 0.000
profit_factor 1.286 1.286 0.000
test_accuracy 0.986 0.986 0.000

Iteration 3: k_loop_iter_3_53ceb1

Y Label: — | Parent FS: #7

Objective mode: scalarize

Scalar score: 1.7212

MetricBaselineModifiedDiff
win_rate 0.553 0.571 0.018
max_drawdown 0.075 0.051 -0.023
sharpe_ratio 7.879 14.382 6.503
profit_factor 1.286 1.604 0.318
test_accuracy 0.986 0.986 0.000

📁 Offline Report

Markdown backup: reports/autoloop/zz_sylvain/20260718_115810.md