feat: implement GBPUSD volatility compression expansion 1m strategy (closes #204)

ideas/idea-002-gbpusd-volatility-compression-expansion-1m.md

@@ -41,4 +41,4 @@ GBPUSD may show repeatable behavior when volatility compression expansion condit
 
 This idea is intentionally Markdown-only. A future template can add `strategy.py`, `quant.config.json`, and a focused README once PPE results justify turning the idea into executable code.
 
-Closes #3
+Closes #204

templates/gbpusd-volatility-compression-expansion-1m/README.md

@@ -0,0 +1,47 @@
+# GBPUSD Volatility Compression Expansion 1m
+
+This strategy implements a volatility compression expansion approach for GBPUSD on 1-minute candles using LogisticRegression.
+
+## Overview
+
+- **Pair**: GBPUSD
+- **Timeframe**: 1m
+- **Model**: LogisticRegression with feature engineering focused on volatility compression/expansion patterns
+- **Goal**: Capture breakouts following periods of low volatility (compression) that expand into high volatility moves
+
+## Features Engineered
+
+1. **Returns**: 1, 3, 6, 12 period returns
+2. **ATR-normalized price action**: Range percentage, body percentage, close position
+3. **Volatility compression/expansion**:
+   - ATR ratio (current vs 50-period average)
+   - ATR percentile (200-period ranking)
+   - Returns-based volatility metrics (fast/slow ratio, percentile)
+   - Bollinger Band width and ratio
+   - Keltner Channel width and ratio
+4. **EMA distances**: From 20, 50, and 200 period EMAs
+5. **Swing points**: Distance to recent swing high/low
+6. **Volume features**: Z-score and ratio to moving average
+
+## Configuration
+
+See `quant.config.json` for hyperparameters:
+- `lookback`: 100 candles for prediction
+- `horizon`: 1 candle forward for labeling
+- `threshold`: 0.0008 (8 pips) for ATR-normalized breakout
+- `min_confidence`: 0.55 minimum probability for signal generation
+
+## Usage
+
+This template follows the PyP Quant Mode contract:
+```python
+def train(data, config):
+    return model, metrics
+
+def predict(model, market_data, config):
+    return {"signal": "UP|DOWN|HOLD", "confidence": 0.0, "metadata": {}}
+```
+
+## Disclaimer
+
+Educational template only. Not financial advice. Past performance does not guarantee future results.

templates/gbpusd-volatility-compression-expansion-1m/quant.config.json

@@ -0,0 +1,28 @@
+{
+  "pair": "GBPUSD",
+  "timeframe": "1m",
+  "model_family": "sklearn LogisticRegression",
+  "runtime_target": "edge",
+  "artifact_format": "weights_bundle",
+  "parameters": {
+    "lookback": 100,
+    "horizon": 1,
+    "threshold": 0.0008,
+    "min_confidence": 0.55
+  },
+  "training_requirements": [
+    "numpy",
+    "pandas",
+    "scikit-learn",
+    "joblib"
+  ],
+  "inference_requirements": [
+    "numpy",
+    "pandas",
+    "scikit-learn",
+    "joblib"
+  ],
+  "symbol": "GBPUSD",
+  "description": "GBPUSD volatility compression expansion strategy using LogisticRegression",
+  "disclaimer": "Educational template only. Not financial advice."
+}

templates/gbpusd-volatility-compression-expansion-1m/strategy.py

@@ -0,0 +1,155 @@
+import numpy as np
+import pandas as pd
+from sklearn.linear_model import LogisticRegression
+from sklearn.pipeline import Pipeline
+from sklearn.preprocessing import StandardScaler
+
+
+SYMBOL = "GBPUSD"
+MODEL_NAME = "gbpusd-volatility-compression-expansion-1m"
+
+
+def _normalise(data):
+    df = data.copy()
+    df.columns = [str(c).lower() for c in df.columns]
+    if "volume" not in df.columns:
+        df["volume"] = 1.0
+    for col in ["open", "high", "low", "close", "volume"]:
+        df[col] = pd.to_numeric(df[col], errors="coerce")
+    return df.dropna(subset=["open", "high", "low", "close"]).reset_index(drop=True)
+
+
+def _features(df):
+    c = df["close"]
+    h = df["high"]
+    l = df["low"]
+    v = df["volume"]
+    
+    # Basic returns
+    out = pd.DataFrame(index=df.index)
+    out["ret1"] = c.pct_change()
+    out["ret3"] = c.pct_change(3)
+    out["ret6"] = c.pct_change(6)
+    out["ret12"] = c.pct_change(12)
+    
+    # ATR for normalization
+    tr = np.maximum(h - l, np.maximum(abs(h - c.shift(1)), abs(l - c.shift(1))))
+    atr = pd.Series(tr).rolling(14).mean()
+    out["atr"] = atr
+    
+    # ATR-normalized candle range and close location value
+    out["range_pct"] = (h - l) / c
+    out["body_pct"] = (c - df["open"]) / (h - l).replace(0, np.nan)
+    out["close_pos"] = (c - l) / (h - l).replace(0, np.nan)
+    
+    # Volatility compression/expansion features
+    # Current ATR relative to historical ATR
+    out["atr_ratio"] = out["atr"] / out["atr"].rolling(50).mean()
+    out["atr_percentile"] = out["atr"].rolling(200).apply(
+        lambda x: pd.Series(x).rank(pct=True).iloc[-1] if len(x) > 0 else 0.5, raw=False)
+    
+    # Volatility percentiles (from idea)
+    returns = c.pct_change()
+    out["volatility_fast"] = returns.rolling(16).std()
+    out["volatility_slow"] = returns.rolling(64).std()
+    out["volatility_ratio"] = out["volatility_fast"] / (out["volatility_slow"] + 1e-9)
+    out["volatility_percentile"] = out["volatility_fast"].rolling(200).apply(
+        lambda x: pd.Series(x).rank(pct=True).iloc[-1] if len(x) > 0 else 0.5, raw=False)
+    
+    # Distance from EMAs
+    out["ema20_dist"] = (c - c.ewm(span=20, adjust=False).mean()) / c
+    out["ema50_dist"] = (c - c.ewm(span=50, adjust=False).mean()) / c
+    out["ema200_dist"] = (c - c.ewm(span=200, adjust=False).mean()) / c
+    
+    # Prior swing high and swing low distance
+    swing_high = h.rolling(20, center=False).max().shift(1)
+    swing_low = l.rolling(20, center=False).min().shift(1)
+    out["dist_to_swing_high"] = (swing_high - c) / c
+    out["dist_to_swing_low"] = (c - swing_low) / c
+    
+    # Volume features
+    out["volume_z"] = (v - v.rolling(48).mean()) / (v.rolling(48).std() + 1e-9)
+    out["volume_ratio"] = v / v.rolling(20).mean()
+    
+    # Bollinger Band width (volatility indicator)
+    sma_20 = c.rolling(20).mean()
+    std_20 = c.rolling(20).std()
+    upper_bb = sma_20 + (std_20 * 2)
+    lower_bb = sma_20 - (std_20 * 2)
+    out["bb_width"] = (upper_bb - lower_bb) / sma_20
+    out["bb_width_ratio"] = out["bb_width"] / out["bb_width"].rolling(50).mean()
+    
+    # Keltner Channel width (ATR-based volatility)
+    ema_20 = c.ewm(span=20, adjust=False).mean()
+    atr_20 = out["atr"].rolling(20).mean()
+    upper_kc = ema_20 + (atr_20 * 1.5)
+    lower_kc = ema_20 - (atr_20 * 1.5)
+    out["kc_width"] = (upper_kc - lower_kc) / ema_20
+    out["kc_width_ratio"] = out["kc_width"] / out["kc_width"].rolling(50).mean()
+    
+    return out.replace([np.inf, -np.inf], np.nan).dropna()
+
+
+def _labels(close, index, horizon, threshold):
+    fwd = close.pct_change(horizon).shift(-horizon)
+    y = pd.Series(1, index=close.index)
+    y[fwd > threshold] = 2
+    y[fwd < -threshold] = 0
+    return y.reindex(index).fillna(1).astype(int)
+
+
+def train(data, config):
+    params = config.get("parameters", {})
+    horizon = int(params.get("horizon", 1))
+    threshold = float(params.get("threshold", 0.0008))
+    df = _normalise(data)
+    feat = _features(df)
+    y = _labels(df["close"], feat.index, horizon, threshold)
+    
+    model = Pipeline([
+        ("scaler", StandardScaler()),
+        ("clf", LogisticRegression(max_iter=1000, class_weight="balanced", multi_class="auto", C=0.1)),
+    ])
+    model.fit(feat.values.astype(np.float32), y.values)
+    preds = model.predict(feat.values.astype(np.float32))
+    
+    metrics = {
+        "training_bars": int(len(feat)),
+        "feature_count": int(feat.shape[1]),
+        "buy_signals": int((preds == 2).sum()),
+        "sell_signals": int((preds == 0).sum()),
+        "hold_signals": int((preds == 1).sum()),
+    }
+    return {"model": model, "features": list(feat.columns), "symbol": SYMBOL}, metrics
+
+
+def predict(model, market_data, config):
+    params = config.get("parameters", {})
+    lookback = int(params.get("lookback", 100))
+    min_conf = float(params.get("min_confidence", 0.55))
+    candles = market_data.get("candles", [])
+    
+    if len(candles) < lookback:
+        return {"signal": "HOLD", "confidence": 0.0, "metadata": {"reason": "not_enough_candles", "model": MODEL_NAME}}
+    
+    df = _normalise(pd.DataFrame(candles, columns=["open", "high", "low", "close", "volume"]))
+    feat = _features(df).tail(1)
+    
+    if feat.empty:
+        return {"signal": "HOLD", "confidence": 0.0, "metadata": {"reason": "no_features", "model": MODEL_NAME}}
+    
+    proba = model["model"].predict_proba(feat.values.astype(np.float32))[0]
+    klass = int(np.argmax(proba))
+    conf = float(proba[klass])
+    signal = {0: "DOWN", 1: "HOLD", 2: "UP"}[klass]
+    
+    if conf < min_conf:
+        signal = "HOLD"
+    
+    return {"signal": signal, "confidence": round(conf, 4), "metadata": {
+        "p_sell": round(float(proba[0]), 4), 
+        "p_hold": round(float(proba[1]), 4), 
+        "p_buy": round(float(proba[2]), 4), 
+        "model": MODEL_NAME, 
+        "symbol": SYMBOL
+    }}