perf(qav3): pivot labeling optimization adaptation to more market

conditions

Signed-off-by: Jérôme Benoit <jerome.benoit@piment-noir.org>

diff --git a/quickadapter/user_data/freqaimodels/QuickAdapterRegressorV3.py b/quickadapter/user_data/freqaimodels/QuickAdapterRegressorV3.py
index 14c4a1178bee9bef752841d171c88f1e499bda99..d6ae4e823abb3aff73b55366a696bec673174d80 100644 (file)
--- a/quickadapter/user_data/freqaimodels/QuickAdapterRegressorV3.py
+++ b/quickadapter/user_data/freqaimodels/QuickAdapterRegressorV3.py
@@ -1541,10 +1541,10 @@ def label_objective(
     candles_step: int,
 ) -> tuple[float, int]:
     min_label_period_candles: int = round_to_nearest_int(
-        max(fit_live_predictions_candles // 18, candles_step), candles_step
+        max(fit_live_predictions_candles // 22, candles_step), candles_step
     )
     max_label_period_candles: int = round_to_nearest_int(
-        max(fit_live_predictions_candles // 3, min_label_period_candles),
+        max(fit_live_predictions_candles // 2, min_label_period_candles),
         candles_step,
     )
     label_period_candles = trial.suggest_int(
@@ -1553,7 +1553,7 @@ def label_objective(
         max_label_period_candles,
         step=candles_step,
     )
-    label_natr_ratio = trial.suggest_float("label_natr_ratio", 3.0, 18.0, step=0.01)
+    label_natr_ratio = trial.suggest_float("label_natr_ratio", 2.0, 22.0, step=0.01)
 
     df = df.iloc[
         -(