Feature Iteration Run #1025

📊 Iterations

Iter	Y Label	Model	Warm	Proxy	Parent FS	Feature	DSL	DSL Valid	p-value	Result	Reason
1	`C8`	`lightgbm`	—	—	#7	k_loop_iter_1_b1169a	`o_div_amplitude_12 * (1 - price_positio…`	✅	1.000	❌ REJECT	1-trial proxy PF=0.000 < 0.95, no improvement expected
2	`C8`	`lightgbm`	—	—	#7	k_iter2_k_high_pct_change_atr_norm_price_position	`k_high.pct_change(12) / (1 + atr_norm) …`	❌	1.000	❌ REJECT	quality_gate: C8 leakage: ['dist_to_high']
3	`C8`	`lightgbm`	—	—	#7	k_iter3_i_rsi_k_close_hl_range_atr_norm	`i_rsi(k_close, 14) * (1 + hl_range) / (…`	❌	1.000	❌ REJECT	quality_gate: NaN ratio 1.000 exceeds 0.3
4	`C8`	`lightgbm`	—	—	#7	k_loop_iter_4_675ba5	`k_volume.pct_change(12) * (1 - hl_range…`	✅	1.000	❌ REJECT	1-trial proxy PF=0.000 < 0.95, no improvement expected
5	`C8`	`lightgbm`	—	—	#7	k_loop_iter_5_73ff25	`i_macd(k_close, 12, 26, 9) * obv_rebase…`	✅	1.000	❌ REJECT	1-trial proxy PF=0.000 < 0.95, no improvement expected
6	`C8`	`lightgbm`	—	—	#7	k_loop_iter_6_785fe7	`k_momentum_pct_change * obv_ensemble_3 …`	✅	1.000	❌ REJECT	1-trial proxy PF=0.000 < 0.95, no improvement expected
7	`C8`	`lightgbm`	—	—	#7	k_loop_iter_7_989ca1	`(o_div_amplitude_12 - k_momentum_pct_ch…`	✅	1.000	❌ REJECT	1-trial proxy PF=0.000 < 0.95, no improvement expected
8	`C8`	`lightgbm`	—	—	#7	k_loop_iter_8_b92879	`i_macd(k_close, 12, 26, 9) / (1 + atr_n…`	✅	1.000	❌ REJECT	1-trial proxy PF=0.000 < 0.95, no improvement expected
9	`C8`	`lightgbm`	—	—	#7	k_iter9_i_atr_k_high_k_low_k_close	`i_atr(k_high, k_low, k_close, 14) / k_c…`	❌	1.000	❌ REJECT	quality_gate: NaN ratio 1.000 exceeds 0.3
10	`C8`	`lightgbm`	—	—	#7	k_iter10_k_volume_rolling_mean_i_atr	`(k_volume / (k_volume.rolling(20).mean(…`	❌	1.000	❌ REJECT	safe_eval DSL produces inf when ['k_close'] is zero; avoid unprotected division by these variables
11	`C8`	`lightgbm`	—	—	#7	k_iter11_i_macd_k_close_i_atr_k_high	`i_macd(k_close, 12, 26, 9) / (1 + i_atr…`	❌	1.000	❌ REJECT	quality_gate: NaN ratio 1.000 exceeds 0.3
12	`C8`	`lightgbm`	—	—	#7	k_iter12_i_macd_k_close_pct_change_i_atr	`i_macd(k_close, 12, 26, 9) * obv_rebase…`	❌	1.000	❌ REJECT	safe_eval DSL triggered unexpected TypeError: unsupported operand type(s) for *: 'float' and 'method'
13	`C8`	`lightgbm`	—	—	#7	k_loop_iter_13_718686	`(k_momentum_pct_change - o_div_amplitud…`	✅	1.000	❌ REJECT	1-trial proxy PF=0.000 < 0.95, no improvement expected
14	`C8`	`lightgbm`	—	—	#7	k_iter14_i_macd_k_close_i_rsi_atr_norm	`i_macd(k_close, 12, 26, 9) / (k_close +…`	❌	1.000	❌ REJECT	quality_gate: NaN ratio 1.000 exceeds 0.3
15	`C8`	`lightgbm`	—	—	#7	k_iter15_abs_k_volume_rolling_mean	`abs(o_div_binary(48)) * k_volume.rollin…`	❌	1.000	❌ REJECT	safe_eval DSL: 變數未定義: abs

📄 Report Markdown

# AUTOLOOP: zz_sylvain (15 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**: 190.70s
> **Total accepted**: 0
> **Total rejected**: 15

## Iterations 詳情

### Iteration 1
- DSL: `o_div_amplitude_12 * (1 - price_position) / (1 + atr_norm * k_momentum_pct_change.abs())` (feature=k_loop_iter_1_b1169a)
- DSL valid: True
- FeatureSet candidate id: 1358
- 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: 1-trial proxy PF=0.000 < 0.95, no improvement expected

### Iteration 2
- DSL: `k_high.pct_change(12) / (1 + atr_norm) * (1 - price_position) * (1 - dist_to_high) * (1 + hl_range) / (1 + return_5)` (feature=k_iter2_k_high_pct_change_atr_norm_price_position)
- 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: C8 leakage: ['dist_to_high']

### Iteration 3
- DSL: `i_rsi(k_close, 14) * (1 + hl_range) / (1 + atr_norm)` (feature=k_iter3_i_rsi_k_close_hl_range_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: quality_gate: NaN ratio 1.000 exceeds 0.3

### Iteration 4
- DSL: `k_volume.pct_change(12) * (1 - hl_range) / (1 + atr_norm) * (1 - return_5)` (feature=k_loop_iter_4_675ba5)
- DSL valid: True
- FeatureSet candidate id: 1359
- 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: 1-trial proxy PF=0.000 < 0.95, no improvement expected

### Iteration 5
- DSL: `i_macd(k_close, 12, 26, 9) * obv_rebased.pct_change(12) / (1 + i_atr(k_high, k_low, k_close, 14) / k_close)` (feature=k_loop_iter_5_73ff25)
- DSL valid: True
- FeatureSet candidate id: 1360
- 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: 1-trial proxy PF=0.000 < 0.95, no improvement expected

### Iteration 6
- DSL: `k_momentum_pct_change * obv_ensemble_3 / (1 + atr_norm * 10) * (1 - price_position)` (feature=k_loop_iter_6_785fe7)
- DSL valid: True
- FeatureSet candidate id: 1361
- 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: 1-trial proxy PF=0.000 < 0.95, no improvement expected

### Iteration 7
- DSL: `(o_div_amplitude_12 - k_momentum_pct_change) / (1 + atr_norm)` (feature=k_loop_iter_7_989ca1)
- DSL valid: True
- FeatureSet candidate id: 1362
- 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: 1-trial proxy PF=0.000 < 0.95, no improvement expected

### Iteration 8
- DSL: `i_macd(k_close, 12, 26, 9) / (1 + atr_norm * 10) * (1 - price_position)` (feature=k_loop_iter_8_b92879)
- DSL valid: True
- FeatureSet candidate id: 1363
- 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: 1-trial proxy PF=0.000 < 0.95, no improvement expected

### Iteration 9
- DSL: `i_atr(k_high, k_low, k_close, 14) / k_close * (1 - i_rsi(k_close, 14) / 100)` (feature=k_iter9_i_atr_k_high_k_low_k_close)
- 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 10
- DSL: `(k_volume / (k_volume.rolling(20).mean() + 1e-10) - 1) * i_atr(k_high, k_low, k_close, 14) / k_close` (feature=k_iter10_k_volume_rolling_mean_i_atr)
- 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 produces inf when ['k_close'] is zero; avoid unprotected division by these variables

### Iteration 11
- DSL: `i_macd(k_close, 12, 26, 9) / (1 + i_atr(k_high, k_low, k_close, 14) / k_close * 10) * i_rsi(k_close, 14) / 100` (feature=k_iter11_i_macd_k_close_i_atr_k_high)
- 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 12
- DSL: `i_macd(k_close, 12, 26, 9) * obv_rebased.pct_change / (1 + i_atr(k_high, k_low, k_close, 14))` (feature=k_iter12_i_macd_k_close_pct_change_i_atr)
- 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 triggered unexpected TypeError: unsupported operand type(s) for *: 'float' and 'method'

### Iteration 13
- DSL: `(k_momentum_pct_change - o_div_amplitude_12) / (1 + atr_norm * 10) * (1 - return_5)` (feature=k_loop_iter_13_718686)
- DSL valid: True
- FeatureSet candidate id: 1364
- 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: 1-trial proxy PF=0.000 < 0.95, no improvement expected

### Iteration 14
- DSL: `i_macd(k_close, 12, 26, 9) / (k_close + 1e-10) * (1 - i_rsi(k_close, 14) / 100) / (1 + atr_norm * 10)` (feature=k_iter14_i_macd_k_close_i_rsi_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: quality_gate: NaN ratio 1.000 exceeds 0.3

### Iteration 15
- DSL: `abs(o_div_binary(48)) * k_volume.rolling.mean / (1 + i_atr(k_high, k_low, k_close, 14) / k_close * 10)` (feature=k_iter15_abs_k_volume_rolling_mean)
- 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: abs

📊 Multi-Objective Metrics

Iteration 1: k_loop_iter_1_b1169a

Y Label: C8 | Parent FS: #7

Objective mode: single

Scalar score: 0.0000

Iteration 2: k_iter2_k_high_pct_change_atr_norm_price_position

Y Label: C8 | Parent FS: #7

Objective mode: single

Scalar score: 0.0000

Iteration 3: k_iter3_i_rsi_k_close_hl_range_atr_norm

Y Label: C8 | Parent FS: #7

Objective mode: single

Scalar score: 0.0000

Iteration 4: k_loop_iter_4_675ba5

Y Label: C8 | Parent FS: #7

Objective mode: single

Scalar score: 0.0000

Iteration 5: k_loop_iter_5_73ff25

Y Label: C8 | Parent FS: #7

Objective mode: single

Scalar score: 0.0000

Iteration 6: k_loop_iter_6_785fe7

Y Label: C8 | Parent FS: #7

Objective mode: single

Scalar score: 0.0000

Iteration 7: k_loop_iter_7_989ca1

Y Label: C8 | Parent FS: #7

Objective mode: single

Scalar score: 0.0000

Iteration 8: k_loop_iter_8_b92879

Y Label: C8 | Parent FS: #7

Objective mode: single

Scalar score: 0.0000

Iteration 9: k_iter9_i_atr_k_high_k_low_k_close

Y Label: C8 | Parent FS: #7

Objective mode: single

Scalar score: 0.0000

Iteration 10: k_iter10_k_volume_rolling_mean_i_atr

Y Label: C8 | Parent FS: #7

Objective mode: single

Scalar score: 0.0000

Iteration 11: k_iter11_i_macd_k_close_i_atr_k_high

Y Label: C8 | Parent FS: #7

Objective mode: single

Scalar score: 0.0000

Iteration 12: k_iter12_i_macd_k_close_pct_change_i_atr

Y Label: C8 | Parent FS: #7

Objective mode: single

Scalar score: 0.0000

Iteration 13: k_loop_iter_13_718686

Y Label: C8 | Parent FS: #7

Objective mode: single

Scalar score: 0.0000

Iteration 14: k_iter14_i_macd_k_close_i_rsi_atr_norm

Y Label: C8 | Parent FS: #7

Objective mode: single

Scalar score: 0.0000

Iteration 15: k_iter15_abs_k_volume_rolling_mean

Y Label: C8 | Parent FS: #7

Objective mode: single

Scalar score: 0.0000

📁 Offline Report

Markdown backup: reports/autoloop/zz_sylvain/20260726_234053.md

Feature Iteration Run #1025: zz_sylvain

📊 Iterations

📄 Report Markdown

📊 Multi-Objective Metrics

Iteration 1: k_loop_iter_1_b1169a

Iteration 2: k_iter2_k_high_pct_change_atr_norm_price_position

Iteration 3: k_iter3_i_rsi_k_close_hl_range_atr_norm

Iteration 4: k_loop_iter_4_675ba5

Iteration 5: k_loop_iter_5_73ff25

Iteration 6: k_loop_iter_6_785fe7

Iteration 7: k_loop_iter_7_989ca1

Iteration 8: k_loop_iter_8_b92879

Iteration 9: k_iter9_i_atr_k_high_k_low_k_close

Iteration 10: k_iter10_k_volume_rolling_mean_i_atr

Iteration 11: k_iter11_i_macd_k_close_i_atr_k_high

Iteration 12: k_iter12_i_macd_k_close_pct_change_i_atr

Iteration 13: k_loop_iter_13_718686

Iteration 14: k_iter14_i_macd_k_close_i_rsi_atr_norm

Iteration 15: k_iter15_abs_k_volume_rolling_mean

📁 Offline Report