Feature Iteration Run #831: zz_sylvain

# AUTOLOOP: zz_sylvain (4 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**: 116.05s
> **Total accepted**: 2
> **Total rejected**: 2

## Iterations 詳情

### Iteration 1
- DSL: `obv_ensemble_3 * (1 - dist_to_high) / (1 + atr_norm)` (feature=k_iter1_dist_to_high_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: 變數未定義: obv_ensemble_3

### Iteration 2
- DSL: `k_high.pct_change(12) / (1 + atr_norm) * (1 - price_position) * (1 + hl_range)` (feature=k_loop_iter_2_79482e)
- DSL valid: True
- FeatureSet candidate id: 1145
- baseline PF: 1.286 → modified PF: 2.113
- t_stat: 0.000, p_value: 0.206, cohens_d: 0.478
- scalar_score: 1.4199
- 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 3
- DSL: `k_momentum_pct_change - o_div_amplitude(12) / (1 + atr_norm)` (feature=k_iter3_k_momentum_pct_chang_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: 變數未定義: o_div_amplitude

### Iteration 4
- DSL: `k_high.pct_change(12) * (1 + hl_range) * (1 - price_position) * (1 - dist_to_high)` (feature=k_loop_iter_4_ba012f)
- DSL valid: True
- FeatureSet candidate id: 1146
- baseline PF: 1.286 → modified PF: 2.113
- t_stat: 0.000, p_value: 0.206, cohens_d: 0.478
- scalar_score: 1.4199
- 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