跳到主要內容

Feature Iteration Run #844: zz_sylvain

Status: completed | Started: 2026-07-23 11:51:13 | Ended: 2026-07-23 11:53:01

📊 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 C8 gradient_boosting — — #7 k_loop_iter_1_999e1b k_momentum_pct_change * i_macd(k_close,… ✅ 1.947 1.664 -0.6428 0.000 0.250 0.534 ❌ REJECT min_p=0.250 ≥ 0.05
2 C8 gradient_boosting — — #7 k_loop_iter_2_6179c5 i_rsi(k_close, 14) * (k_high - k_low) /… ✅ 1.947 1.328 -0.3004 0.000 0.404 0.109 ❌ REJECT min_p=0.404 ≥ 0.05

📄 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**: 107.50s
> **Total accepted**: 0
> **Total rejected**: 2

## Iterations 詳情

### Iteration 1
- DSL: `k_momentum_pct_change * i_macd(k_close, 12, 26, 9) / (1 + atr_norm)` (feature=k_loop_iter_1_999e1b)
- DSL valid: True
- FeatureSet candidate id: 1195
- baseline PF: 1.947 → modified PF: 1.664
- t_stat: 0.000, p_value: 0.250, cohens_d: 0.534
- scalar_score: -0.6428
- accepted: False, reason: min_p=0.250 ≥ 0.05

**Metrics summary:**
  - profit_factor: baseline=1.947, modified=1.664, diff=-0.283
  - sharpe_ratio: baseline=19.162, modified=14.844, diff=-4.319
  - win_rate: baseline=0.600, modified=0.525, diff=-0.075
  - max_drawdown: baseline=0.056, modified=0.103, diff=0.047
  - test_accuracy: baseline=0.992, modified=0.992, diff=-0.000

### Iteration 2
- DSL: `i_rsi(k_close, 14) * (k_high - k_low) / (1 + atr_norm)` (feature=k_loop_iter_2_6179c5)
- DSL valid: True
- FeatureSet candidate id: 1196
- baseline PF: 1.947 → modified PF: 1.328
- t_stat: 0.000, p_value: 0.404, cohens_d: 0.109
- scalar_score: -0.3004
- accepted: False, reason: min_p=0.404 ≥ 0.05

**Metrics summary:**
  - profit_factor: baseline=1.947, modified=1.328, diff=-0.620
  - sharpe_ratio: baseline=19.162, modified=7.904, diff=-11.258
  - win_rate: baseline=0.600, modified=0.486, diff=-0.114
  - max_drawdown: baseline=0.056, modified=0.103, diff=0.047
  - test_accuracy: baseline=0.992, modified=0.992, diff=-0.000

📊 Multi-Objective Metrics

Iteration 1: k_loop_iter_1_999e1b

Y Label: C8 | Parent FS: #7

Objective mode: scalarize

Scalar score: -0.6428

MetricBaselineModifiedDiff
win_rate 0.600 0.525 -0.075
max_drawdown 0.056 0.103 0.047
sharpe_ratio 19.162 14.844 -4.319
profit_factor 1.947 1.664 -0.283
test_accuracy 0.992 0.992 0.000

Iteration 2: k_loop_iter_2_6179c5

Y Label: C8 | Parent FS: #7

Objective mode: scalarize

Scalar score: -0.3004

MetricBaselineModifiedDiff
win_rate 0.600 0.486 -0.114
max_drawdown 0.056 0.103 0.047
sharpe_ratio 19.162 7.904 -11.258
profit_factor 1.947 1.328 -0.620
test_accuracy 0.992 0.992 0.000

📁 Offline Report

Markdown backup: reports/autoloop/zz_sylvain/20260723_195301.md