feat: train forecasts on trade outcomes

crypto_spot_bot/strategy.py

@@ -689,7 +689,7 @@ def _torch_forecast_entry_signal(
     sizing = _torch_forecast_position_sizing(settings, account_context, stop_loss_percent, forecast, symbol)
     position_notional = float(sizing["notional_usdt"])
     expected_return = _safe_float(forecast.get("expected_return_percent"), 0.0)
-    probability_up = _safe_float(forecast.get("probability_up"), 0.5)
+    probability_up = _forecast_probability(forecast)
     skill = _safe_float(forecast.get("skill"), 0.0)
     min_edge = max(0.0, _safe_float(forecast.get("calibrated_min_edge_percent"), settings.time_series_min_edge_percent))
     min_probability = _clamp(
@@ -945,7 +945,7 @@ def _torch_forecast_exit_signal(
     )
 
     expected_return = _safe_float(forecast.get("expected_return_percent"), 0.0)
-    probability_up = _safe_float(forecast.get("probability_up"), 0.5)
+    probability_up = _forecast_probability(forecast)
     skill = _safe_float(forecast.get("skill"), 0.0)
     min_edge = max(0.0, _safe_float(forecast.get("calibrated_min_edge_percent"), settings.time_series_min_edge_percent))
     min_probability = _clamp(
@@ -1140,7 +1140,7 @@ def _dynamic_symbol_position_limit(settings: Settings) -> int:
 
 def _torch_forecast_confidence(settings: Settings, forecast: dict) -> float:
     expected_return = max(0.0, _safe_float(forecast.get("expected_return_percent"), 0.0))
-    probability_up = _safe_float(forecast.get("probability_up"), 0.5)
+    probability_up = _forecast_probability(forecast)
     skill = max(0.0, _safe_float(forecast.get("skill"), 0.0))
     min_edge = max(0.01, settings.time_series_min_edge_percent)
     edge_strength = _clamp(expected_return / max(min_edge * 4.0, 0.01), 0.0, 1.0)
@@ -1168,7 +1168,7 @@ def _torch_forecast_position_sizing(
         symbol=symbol,
     )
     expected_return = max(0.0, _safe_float(forecast.get("expected_return_percent"), 0.0))
-    probability_up = _safe_float(forecast.get("probability_up"), 0.5)
+    probability_up = _forecast_probability(forecast)
     skill = max(0.0, _safe_float(forecast.get("skill"), 0.0))
     min_edge = max(0.01, settings.time_series_min_edge_percent)
     edge_multiplier = _clamp(expected_return / max(min_edge * 3.0, 0.01), 0.25, 1.15)
@@ -1323,7 +1323,7 @@ def _position_risk_multiplier(forecast: dict | None, adaptive: dict | None) -> f
     multiplier = 1.0
     forecast = forecast or {}
     if forecast.get("usable"):
-        probability_up = _safe_float(forecast.get("probability_up"), 0.5)
+        probability_up = _forecast_probability(forecast)
         volatility_percent = _safe_float(forecast.get("volatility_percent"), 0.0)
         if probability_up < 0.52:
             multiplier *= 0.75
@@ -1360,7 +1360,7 @@ def _kelly_position(
     probability_source = "confidence"
     probability = confidence_probability
     if forecast.get("usable"):
-        probability = _safe_float(forecast.get("probability_up"), confidence_probability)
+        probability = _forecast_probability(forecast, confidence_probability)
         probability_source = "forecast"
     probability = _clamp(probability, 0.0, 1.0)
 
@@ -1661,6 +1661,13 @@ def _rebound_state(
     }
 
 
+def _forecast_probability(forecast: dict, default: float = 0.5) -> float:
+    value = forecast.get("probability_take_profit_first")
+    if not isinstance(value, (int, float, str)):
+        value = forecast.get("probability_up")
+    return _clamp(_safe_float(value, default), 0.0, 1.0)
+
+
 def _safe_float(value: object, default: float = 0.0) -> float:
     try:
         return float(value)
@@ -1783,7 +1790,7 @@ def _forecast_exit_signal(
         return None
     skill = _safe_float(forecast.get("skill"), 0.0)
     expected_return = _safe_float(forecast.get("expected_return_percent"), 0.0)
-    probability_up = _safe_float(forecast.get("probability_up"), 0.5)
+    probability_up = _forecast_probability(forecast)
     min_edge = max(0.0, min_edge_percent)
     strong_negative = skill > 0.02 and expected_return <= -max(min_edge, 0.03) and probability_up <= 0.44
     if not strong_negative:

crypto_spot_bot/time_series.py

@@ -163,6 +163,7 @@ class TimeSeriesForecast:
     calibrated_min_edge_percent: float = 0.0
     calibrated_min_probability_up: float = 0.0
     calibrated_min_confidence: float = 0.0
+    probability_take_profit_first: float | None = None
 
     def as_dict(self) -> dict[str, Any]:
         return asdict(self)
@@ -254,6 +255,7 @@ class TimeSeriesForecaster:
             expected_gross_return = float(selected.get("expected_gross_return", expected_return))
             expected_price = closes[-1] * math.exp(expected_gross_return)
             probability_up = _clamp(float(selected.get("probability_up", 0.5)), 0.0, 1.0)
+            target_transform = str(entry.get("target_transform", "net_return_over_volatility"))
             model_mae = max(float(selected.get("validation_mae", 0.0)), 1e-9)
             baseline_mae = max(float(selected.get("baseline_mae", model_mae)), model_mae)
             uncertainty = max(float(selected.get("uncertainty", model_mae)), 1e-9)
@@ -279,12 +281,16 @@ class TimeSeriesForecaster:
                 or (expected_return_percent <= -min_edge and probability_up <= 0.45)
                 or (q50_percent <= -min_edge and probability_up <= 0.48)
             )
-            reason = _reason(
-                model=model,
-                expected_return_percent=expected_return_percent,
-                probability_up=probability_up,
-                skill=skill,
-                block_entry=block_entry,
+            reason = (
+                _barrier_reason(model, expected_return_percent, probability_up, skill, block_entry)
+                if target_transform == "barrier_net_return"
+                else _reason(
+                    model=model,
+                    expected_return_percent=expected_return_percent,
+                    probability_up=probability_up,
+                    skill=skill,
+                    block_entry=block_entry,
+                )
             )
             if not symbol_eligible:
                 reason = "symbol excluded by train-only calibration"
@@ -292,7 +298,11 @@ class TimeSeriesForecaster:
                 enabled=True,
                 usable=True,
                 model=model,
-                volatility_model="probabilistic multi-horizon after-cost quantile",
+                volatility_model=(
+                    "TP-before-SL multi-task after-cost model"
+                    if target_transform == "barrier_net_return"
+                    else "probabilistic multi-horizon after-cost quantile"
+                ),
                 expected_return_percent=round(expected_return_percent, 4),
                 expected_price=round(expected_price, 8),
                 volatility_percent=round(volatility_percent, 4),
@@ -309,7 +319,7 @@ class TimeSeriesForecaster:
                 quantile_50_percent=round(q50_percent, 4),
                 quantile_90_percent=round(q90_percent, 4),
                 conservative_return_percent=round(conservative_return_percent, 4),
-                target_transform=str(entry.get("target_transform", "net_return_over_volatility")),
+                target_transform=target_transform,
                 feature_snapshot=feature_snapshot,
                 horizon_forecasts=_public_horizon_forecasts(prediction),
                 candidates=[{"model": model, "mae_percent": round(model_mae * 100, 4)}],
@@ -321,6 +331,11 @@ class TimeSeriesForecaster:
                 calibrated_min_edge_percent=calibrated["edge"],
                 calibrated_min_probability_up=calibrated["probability"],
                 calibrated_min_confidence=calibrated["confidence"],
+                probability_take_profit_first=(
+                    round(probability_up, 4)
+                    if target_transform == "barrier_net_return"
+                    else None
+                ),
             )
 
         direct_horizon = _is_direct_horizon(entry)
@@ -1172,6 +1187,47 @@ def _average_ensemble_predictions(predictions: list[float | dict[str, Any]]) ->
 
 def _torch_head_outputs(context: list[float], entry: dict[str, Any], hidden_size: int) -> list[float]:
     context = _apply_context_norm(context, entry)
+    if entry.get("multitask_head") is True:
+        hidden_matrix = _float_matrix(entry.get("head_hidden_weight"))
+        hidden_bias = _float_vector(entry.get("head_hidden_bias"))
+        if not hidden_matrix or len(hidden_bias) != len(hidden_matrix):
+            return []
+        shared = [
+            _gelu(_dot(row, context) + hidden_bias[index])
+            for index, row in enumerate(hidden_matrix)
+            if len(row) == hidden_size
+        ]
+        if len(shared) != len(hidden_matrix):
+            return []
+        return_matrix = _float_matrix(entry.get("return_head_weight"))
+        return_bias = _float_vector(entry.get("return_head_bias"))
+        event_matrix = _float_matrix(entry.get("event_head_weight"))
+        event_bias = _float_vector(entry.get("event_head_bias"))
+        if (
+            not return_matrix
+            or len(return_bias) != len(return_matrix)
+            or not event_matrix
+            or len(event_bias) != len(event_matrix)
+        ):
+            return []
+        return_values = [
+            _dot(row, shared) + return_bias[index]
+            for index, row in enumerate(return_matrix)
+            if len(row) == len(shared)
+        ]
+        event_values = [
+            _dot(row, shared) + event_bias[index]
+            for index, row in enumerate(event_matrix)
+            if len(row) == len(shared)
+        ]
+        if len(return_values) != len(event_values) * 4:
+            return []
+        outputs: list[float] = []
+        for horizon_index, event_value in enumerate(event_values):
+            base = horizon_index * 4
+            outputs.extend(return_values[base : base + 4])
+            outputs.append(event_value)
+        return outputs
     raw_weight = entry.get("head_weight")
     if isinstance(raw_weight, list) and raw_weight and isinstance(raw_weight[0], list):
         matrix = _float_matrix(raw_weight)
@@ -1242,8 +1298,18 @@ def _decode_multi_horizon_prediction(
 
         expected = decode("mean")
         q_values = sorted([decode("q10", expected), decode("q50", expected), decode("q90", expected)])
-        probability_up = _sigmoid(float(values.get("logit_up", 0.0)))
+        probability_up = _sigmoid(
+            float(values.get("logit_tp_first", values.get("logit_up", 0.0)))
+        )
         cap = _prediction_cap(closes, horizon, round_trip_cost)
+        if str(entry.get("target_transform", "")) == "barrier_net_return":
+            stop_percent = _clamp(_float_entry(entry, "target_stop_loss_percent", 0.04), 0.003, 0.08)
+            take_percent = _clamp(_float_entry(entry, "target_take_profit_percent", 0.035), 0.003, 0.20)
+            cap = max(
+                cap,
+                abs(math.log(1.0 - stop_percent) - round_trip_cost),
+                abs(math.log(1.0 + take_percent) - round_trip_cost),
+            )
         expected = _clamp(expected, -cap, cap)
         q10 = _clamp(q_values[0], -cap, cap)
         q50 = _clamp(q_values[1], -cap, cap)
@@ -1267,6 +1333,11 @@ def _decode_multi_horizon_prediction(
             "q50": q50,
             "q90": q90,
             "probability_up": probability_up,
+            "probability_take_profit_first": (
+                probability_up
+                if str(entry.get("target_transform", "")) == "barrier_net_return"
+                else None
+            ),
             "volatility_scale": vol_scale,
             "validation_mae": mae,
             "baseline_mae": base_mae,
@@ -1697,6 +1768,10 @@ def _public_horizon_forecasts(prediction: dict[str, Any]) -> dict[str, Any]:
             "quantile_50_percent": round((math.exp(float(row.get("q50", 0.0))) - 1) * 100, 4),
             "quantile_90_percent": round((math.exp(float(row.get("q90", 0.0))) - 1) * 100, 4),
         }
+        if isinstance(row.get("probability_take_profit_first"), (int, float)):
+            public[key]["probability_take_profit_first"] = round(
+                _clamp(float(row["probability_take_profit_first"]), 0.0, 1.0), 4
+            )
     return public
 
 
@@ -1728,6 +1803,10 @@ def _dot(left: list[float], right: list[float]) -> float:
     return sum(left[index] * right[index] for index in range(min(len(left), len(right))))
 
 
+def _gelu(value: float) -> float:
+    return 0.5 * value * (1.0 + math.erf(value / math.sqrt(2.0)))
+
+
 def _return_scale(returns: list[float]) -> float:
     recent = returns[-120:] if len(returns) > 120 else returns
     values = sorted(abs(value) for value in recent if math.isfinite(value))
@@ -1772,6 +1851,41 @@ def _prediction_cap(closes: list[float], horizon: int, round_trip_cost: float) -
     return max(base * 1.5 + round_trip_cost, 0.0005)
 
 
+def _barrier_outcome(
+    candles: list[Candle],
+    *,
+    end_index: int,
+    horizon: int,
+    stop_loss_percent: float,
+    take_profit_percent: float,
+    round_trip_cost: float,
+) -> tuple[float, float] | None:
+    """Return after-cost log PnL and whether TP was reached before SL."""
+    entry_index = end_index + 1
+    exit_index = end_index + max(1, horizon)
+    if entry_index >= len(candles) or exit_index >= len(candles):
+        return None
+    entry = float(candles[entry_index].open)
+    if entry <= 0:
+        return None
+    stop = entry * (1.0 - _clamp(stop_loss_percent, 0.003, 0.08))
+    take = entry * (1.0 + _clamp(take_profit_percent, 0.003, 0.20))
+    for index in range(entry_index, exit_index + 1):
+        candle = candles[index]
+        stop_hit = float(candle.low) <= stop
+        take_hit = float(candle.high) >= take
+        # OHLC data cannot reveal intrabar ordering, so ties are resolved
+        # conservatively as stop-loss first.
+        if stop_hit:
+            return math.log(stop / entry) - round_trip_cost, 0.0
+        if take_hit:
+            return math.log(take / entry) - round_trip_cost, 1.0
+    terminal = float(candles[exit_index].close)
+    if terminal <= 0:
+        return None
+    return math.log(terminal / entry) - round_trip_cost, 0.0
+
+
 def _sigmoid(value: float) -> float:
     if value >= 40:
         return 1.0
@@ -1813,6 +1927,21 @@ def _reason(
     return f"model {model}: forecast {expected_return_percent:.3f}%, P(up)={probability_up:.2f}, skill={skill:.3f}"
 
 
+def _barrier_reason(
+    model: str,
+    expected_return_percent: float,
+    probability_take_profit_first: float,
+    skill: float,
+    block_entry: bool,
+) -> str:
+    state = "entry blocked" if block_entry else "entry evaluated"
+    return (
+        f"model {model}: expected net {expected_return_percent:.3f}%, "
+        f"P(TP before SL)={probability_take_profit_first:.2f}, "
+        f"skill={skill:.3f}; {state}"
+    )
+
+
 def _normal_cdf(value: float) -> float:
     return 0.5 * (1 + math.erf(value / math.sqrt(2)))
 

crypto_spot_bot/training_coordination.py

@@ -379,11 +379,19 @@ def _safe_parameters(value: Any) -> dict[str, Any]:
         "layers",
         "dropouts",
         "epochs",
+        "validation_window",
         "holdout_window",
         "ensemble_seeds",
         "selection_folds",
         "learning_rate",
         "weight_decay",
+        "horizon",
+        "horizons",
+        "patience",
+        "context_symbols",
+        "features",
+        "seed",
+        "interval",
         "pooled",
         "resume_candidate",
     }
@@ -391,8 +399,12 @@ def _safe_parameters(value: Any) -> dict[str, Any]:
     for key, low, high in (
         ("limit", 500, 20000),
         ("epochs", 1, 200),
+        ("validation_window", 64, 2000),
         ("holdout_window", 64, 1000),
         ("selection_folds", 1, 12),
+        ("horizon", 1, 96),
+        ("patience", 1, 50),
+        ("seed", 1, 2_147_483_647),
     ):
         if key not in result:
             continue
@@ -414,9 +426,19 @@ def _safe_parameters(value: Any) -> dict[str, Any]:
             if item.strip().lower() in {"lstm", "gru"}
         ]
         result["architectures"] = ",".join(architectures) or "lstm,gru"
-    for key in ("lookbacks", "hidden_sizes", "layers", "dropouts", "ensemble_seeds"):
+    for key in (
+        "lookbacks",
+        "hidden_sizes",
+        "layers",
+        "dropouts",
+        "ensemble_seeds",
+        "horizons",
+        "context_symbols",
+        "features",
+        "interval",
+    ):
         if key in result:
-            result[key] = str(result[key])[:200]
+            result[key] = str(result[key])[: 4000 if key == "features" else 500]
     for key, low, high in (
         ("learning_rate", 0.00001, 0.1),
         ("weight_decay", 0.0, 0.1),
@@ -471,10 +493,27 @@ def _validate_symbol_models(symbols: dict[str, Any]) -> None:
             raise ValueError(f"candidate model dimensions are invalid: {symbol}") from exc
         if not 4 <= lookback <= 512 or not 1 <= input_size <= 256 or not 1 <= hidden_size <= 1024:
             raise ValueError(f"candidate model dimensions are out of range: {symbol}")
-        if not isinstance(entry.get("state_dict"), dict):
-            raise ValueError(f"candidate recurrent state is missing: {symbol}")
-        if not isinstance(entry.get("head_weight"), list) or not isinstance(entry.get("head_bias"), list):
-            raise ValueError(f"candidate forecast head is missing: {symbol}")
+        members = entry.get("ensemble_members")
+        payloads = members if isinstance(members, list) and members else [entry]
+        for payload in payloads:
+            if not isinstance(payload, dict) or not isinstance(payload.get("state_dict"), dict):
+                raise ValueError(f"candidate recurrent state is missing: {symbol}")
+            merged = {**entry, **payload}
+            if merged.get("multitask_head") is True:
+                required = (
+                    "head_hidden_weight",
+                    "head_hidden_bias",
+                    "return_head_weight",
+                    "return_head_bias",
+                    "event_head_weight",
+                    "event_head_bias",
+                )
+                if any(not isinstance(merged.get(name), list) for name in required):
+                    raise ValueError(f"candidate multitask forecast head is missing: {symbol}")
+            elif not isinstance(merged.get("head_weight"), list) or not isinstance(
+                merged.get("head_bias"), list
+            ):
+                raise ValueError(f"candidate forecast head is missing: {symbol}")
 
 
 def _compact_now() -> str: