feat(ml): relax training thresholds for 5-10x more training samples

Add TRAIN_* constants (signal_threshold=2, adx=15, vol_mult=1.5, neg_ratio=3)
as dataset_builder defaults. Remove hardcoded negative_ratio=5 from all callers.
Bot entry conditions unchanged (config.py strict values).

WF 5-fold results (all symbols AUC 0.91+):
- XRPUSDT: 0.9216 ± 0.0052
- SOLUSDT:  0.9174 ± 0.0063
- DOGEUSDT: 0.9222 ± 0.0085

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

src/backtester.py

@@ -598,7 +598,7 @@ class WalkForwardConfig(BacktestConfig):
     train_months: int = 6       # 학습 윈도우 (개월)
     test_months: int = 1        # 검증 윈도우 (개월)
     time_weight_decay: float = 2.0
-    negative_ratio: int = 5
+    negative_ratio: int = 3
 
 
 class WalkForwardBacktester: