跳到主要內容

Feature Iteration Run #981: zz_sylvain

Status: completed | Started: 2026-07-26 00:40:34 | Ended: 2026-07-26 00:43:30

⭐ Best Accepted Iteration

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

baseline PF: 1.947 → modified PF: 2.610 | Cohen's d: 0.607 | p-value: 0.000

📊 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 C8 gradient_boosting — — #7 k_loop_iter_1_ac5f81 i_macd(k_close, 12, 26, 9) * (1 - price… ✅ 1.947 1.895 -0.1089 0.000 0.337 0.330 ❌ REJECT normalized_score -0.0230 <= 0.0, sharpe_delta -0.9574 < -0.1, hypothesis test not confirmed
2 C8 gradient_boosting — — #7 k_loop_iter_2_e0b8fa k_high.pct_change(12) * (1 + hl_range) … ✅ 1.947 2.610 2.2754 0.000 0.000 0.607 ✅ ACCEPT accepted
3 C8 gradient_boosting — — #1254 k_loop_iter_3_5cf9bc o_pct_change_12 * (1 + hl_range) * (1 -… ✅ 2.610 2.189 -1.4964 0.000 0.000 0.310 ❌ REJECT normalized_score -0.0799 <= 0.0, sharpe_delta -5.0623 < -0.1, hypothesis test not confirmed

📄 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**: 1254
> **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**: 176.22s
> **Total accepted**: 1
> **Total rejected**: 2

## Iterations 詳情

### Iteration 1
- DSL: `i_macd(k_close, 12, 26, 9) * (1 - price_position) * (1 + hl_range) / (1 + atr_norm * 10)` (feature=k_loop_iter_1_ac5f81)
- DSL valid: True
- FeatureSet candidate id: 1253
- baseline PF: 1.947 → modified PF: 1.895
- t_stat: 0.000, p_value: 0.337, cohens_d: 0.330
- scalar_score: -0.1089
- accepted: False, reason: normalized_score -0.0230 <= 0.0, sharpe_delta -0.9574 < -0.1, hypothesis test not confirmed

**Metrics summary:**
  - profit_factor: baseline=1.947, modified=1.895, diff=-0.053
  - sharpe_ratio: baseline=19.162, modified=18.205, diff=-0.957
  - win_rate: baseline=0.600, modified=0.562, diff=-0.037
  - max_drawdown: baseline=0.056, modified=0.056, diff=0.000
  - test_accuracy: baseline=0.992, modified=0.992, diff=-0.000

### Iteration 2
- DSL: `k_high.pct_change(12) * (1 + hl_range) * (1 - i_macd(k_close, 12, 26, 9))` (feature=k_loop_iter_2_e0b8fa)
- DSL valid: True
- FeatureSet candidate id: 1254
- baseline PF: 1.947 → modified PF: 2.610
- t_stat: 0.000, p_value: 0.000, cohens_d: 0.607
- scalar_score: 2.2754
- accepted: True, reason: accepted

**Metrics summary:**
  - profit_factor: baseline=1.947, modified=2.610, diff=0.663
  - sharpe_ratio: baseline=19.162, modified=26.819, diff=7.657
  - win_rate: baseline=0.600, modified=0.667, diff=0.067
  - max_drawdown: baseline=0.056, modified=0.042, diff=-0.014
  - test_accuracy: baseline=0.992, modified=0.993, diff=0.000

### Iteration 3
- DSL: `o_pct_change_12 * (1 + hl_range) * (1 - i_macd(k_close, 12, 26, 9)) / (1 + atr_norm * 10)` (feature=k_loop_iter_3_5cf9bc)
- DSL valid: True
- FeatureSet candidate id: 1255
- baseline PF: 2.610 → modified PF: 2.189
- t_stat: 0.000, p_value: 0.000, cohens_d: 0.310
- scalar_score: -1.4964
- accepted: False, reason: normalized_score -0.0799 <= 0.0, sharpe_delta -5.0623 < -0.1, hypothesis test not confirmed

**Metrics summary:**
  - profit_factor: baseline=2.610, modified=2.189, diff=-0.422
  - sharpe_ratio: baseline=26.819, modified=21.757, diff=-5.062
  - win_rate: baseline=0.667, modified=0.593, diff=-0.074
  - max_drawdown: baseline=0.042, modified=0.067, diff=0.025
  - test_accuracy: baseline=0.993, modified=0.992, diff=-0.000

📊 Multi-Objective Metrics

Iteration 1: k_loop_iter_1_ac5f81

Y Label: C8 | Parent FS: #7

Objective mode: scalarize

Scalar score: -0.1089

MetricBaselineModifiedDiff
win_rate 0.600 0.563 -0.037
max_drawdown 0.056 0.056 0.000
sharpe_ratio 19.162 18.205 -0.957
profit_factor 1.947 1.895 -0.053
test_accuracy 0.992 0.992 0.000

Iteration 2: k_loop_iter_2_e0b8fa

Y Label: C8 | Parent FS: #7

Objective mode: scalarize

Scalar score: 2.2754

MetricBaselineModifiedDiff
win_rate 0.600 0.667 0.067
max_drawdown 0.056 0.042 -0.014
sharpe_ratio 19.162 26.819 7.657
profit_factor 1.947 2.610 0.663
test_accuracy 0.992 0.993 0.000

Iteration 3: k_loop_iter_3_5cf9bc

Y Label: C8 | Parent FS: #1254

Objective mode: scalarize

Scalar score: -1.4964

MetricBaselineModifiedDiff
win_rate 0.667 0.593 -0.074
max_drawdown 0.042 0.067 0.025
sharpe_ratio 26.819 21.757 -5.062
profit_factor 2.610 2.189 -0.422
test_accuracy 0.993 0.992 0.000

📁 Offline Report

Markdown backup: reports/autoloop/zz_sylvain/20260726_084330.md