跳到主要內容

Feature Iteration Run #837: zz_sylvain

Status: completed | Started: 2026-07-23 04:54:31 | Ended: 2026-07-23 04:56:06

⭐ Best Accepted Iteration

Iteration 2: k_high.pct_change(12) * (1 + hl_range) * (1 - dist_to_high)…

baseline PF: 1.947 → modified PF: 2.466 | Cohen's d: 0.388 | p-value: 0.012

📊 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_iter1_i_macd_k_close_pct_change_atr_norm i_macd(k_close, 12, 26, 9) * obv_rebase… ❌ 0.000 0.000 0.0000 0.000 1.000 0.000 ❌ REJECT safe_eval DSL produced inf values; likely division by zero
2 — gradient_boosting — — #7 k_loop_iter_2_203359 k_high.pct_change(12) * (1 + hl_range) … ✅ 1.947 2.466 1.3886 0.000 0.012 0.388 ✅ ACCEPT accepted
3 — gradient_boosting — — #7 k_loop_iter_3_28bb2c k_momentum_pct_change * (1 + hl_range) … ✅ 1.947 0.775 -3.3916 0.000 0.278 0.577 ❌ REJECT min_p=0.278 ≥ 0.05, constraints: ['sharpe_ratio >= 1.0: got -7.5544']

📄 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**: 94.94s
> **Total accepted**: 1
> **Total rejected**: 2

## Iterations 詳情

### Iteration 1
- DSL: `i_macd(k_close, 12, 26, 9) * obv_rebased.pct_change(12) / (1 + atr_norm)` (feature=k_iter1_i_macd_k_close_pct_change_atr_norm)
- DSL valid: False
- FeatureSet candidate id: None
- baseline PF: 0.000 → modified PF: 0.000
- t_stat: 0.000, p_value: 1.000, cohens_d: 0.000
- scalar_score: 0.0000
- accepted: False, reason: safe_eval DSL produced inf values; likely division by zero

### Iteration 2
- DSL: `k_high.pct_change(12) * (1 + hl_range) * (1 - dist_to_high) / (1 + atr_norm)` (feature=k_loop_iter_2_203359)
- DSL valid: True
- FeatureSet candidate id: 1173
- baseline PF: 1.947 → modified PF: 2.466
- t_stat: 0.000, p_value: 0.012, cohens_d: 0.388
- scalar_score: 1.3886
- accepted: True, reason: accepted

**Metrics summary:**
  - profit_factor: baseline=1.947, modified=2.466, diff=0.519
  - sharpe_ratio: baseline=19.162, modified=24.727, diff=5.565
  - win_rate: baseline=0.600, modified=0.636, diff=0.036
  - max_drawdown: baseline=0.056, modified=0.050, diff=-0.006
  - test_accuracy: baseline=0.992, modified=0.992, diff=-0.000

### Iteration 3
- DSL: `k_momentum_pct_change * (1 + hl_range) - o_div_amplitude_12 / (1 + atr_norm)` (feature=k_loop_iter_3_28bb2c)
- DSL valid: True
- FeatureSet candidate id: 1174
- baseline PF: 1.947 → modified PF: 0.775
- t_stat: 0.000, p_value: 0.278, cohens_d: 0.577
- scalar_score: -3.3916
- accepted: False, reason: min_p=0.278 ≥ 0.05, constraints: ['sharpe_ratio >= 1.0: got -7.5544']

**Metrics summary:**
  - profit_factor: baseline=1.947, modified=0.775, diff=-1.172
  - sharpe_ratio: baseline=19.162, modified=-7.554, diff=-26.717
  - win_rate: baseline=0.600, modified=0.424, diff=-0.176
  - max_drawdown: baseline=0.056, modified=0.131, diff=0.075
  - test_accuracy: baseline=0.992, modified=0.992, diff=-0.001

📊 Multi-Objective Metrics

Iteration 1: k_iter1_i_macd_k_close_pct_change_atr_norm

Y Label: — | Parent FS: #7

Objective mode: single

Scalar score: 0.0000

Iteration 2: k_loop_iter_2_203359

Y Label: — | Parent FS: #7

Objective mode: scalarize

Scalar score: 1.3886

MetricBaselineModifiedDiff
win_rate 0.600 0.636 0.036
max_drawdown 0.056 0.050 -0.006
sharpe_ratio 19.162 24.727 5.565
profit_factor 1.947 2.466 0.519
test_accuracy 0.992 0.992 0.000

Iteration 3: k_loop_iter_3_28bb2c

Y Label: — | Parent FS: #7

Objective mode: scalarize

Scalar score: -3.3916

Failed constraints: sharpe_ratio >= 1.0: got -7.5544

MetricBaselineModifiedDiff
win_rate 0.600 0.424 -0.176
max_drawdown 0.056 0.131 0.075
sharpe_ratio 19.162 -7.554 -26.717
profit_factor 1.947 0.775 -1.172
test_accuracy 0.992 0.992 -0.001

📁 Offline Report

Markdown backup: reports/autoloop/zz_sylvain/20260723_125606.md