Feature Iteration Run #983: zz_sylvain

# 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**: 92.76s
> **Total accepted**: 0
> **Total rejected**: 3

## Iterations 詳情

### Iteration 1
- DSL: `o_pct_change_12 * (1 - i_rsi(k_close, 14) / 50) / (1 + atr_norm * i_ema(k_volume, 20))` (feature=k_iter1_i_rsi_k_close_atr_norm_i_ema)
- 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: quality_gate: NaN ratio 1.000 exceeds 0.3

### Iteration 2
- DSL: `k_high.pct_change(12) * (1 + hl_range) * (1 - i_macd(k_close, 12, 26, 9) / k_close) * (1 - price_position)` (feature=k_loop_iter_2_b78bf7)
- DSL valid: True
- FeatureSet candidate id: 1256
- baseline PF: 1.947 → modified PF: 2.709
- t_stat: 0.000, p_value: 0.003, cohens_d: 0.716
- scalar_score: 2.4413
- accepted: False, reason: max_drawdown_delta -0.0268 < -0.02

**Metrics summary:**
  - profit_factor: baseline=1.947, modified=2.709, diff=0.762
  - sharpe_ratio: baseline=19.162, modified=27.345, diff=8.183
  - win_rate: baseline=0.600, modified=0.636, diff=0.036
  - max_drawdown: baseline=0.056, modified=0.029, diff=-0.027
  - test_accuracy: baseline=0.992, modified=0.992, diff=-0.001

### Iteration 3
- DSL: `k_high.pct_change(12) * (1 + hl_range) * (1 - i_rsi(k_close, 14) / 100)` (feature=k_iter3_k_high_pct_change_hl_range_i_rsi)
- 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: quality_gate: NaN ratio 1.000 exceeds 0.3