diff --git a/ideas/idea-005-usdcad-mean-reversion-with-atr-bands-1m.md b/ideas/idea-005-usdcad-mean-reversion-with-atr-bands-1m.md index 0821766..ad4692c 100644 --- a/ideas/idea-005-usdcad-mean-reversion-with-atr-bands-1m.md +++ b/ideas/idea-005-usdcad-mean-reversion-with-atr-bands-1m.md @@ -41,4 +41,4 @@ USDCAD may show repeatable behavior when mean reversion with ATR bands condition 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 #9 +Closes #208 \ No newline at end of file diff --git a/templates/usdcad-mean-reversion-with-atr-bands-1m/README.md b/templates/usdcad-mean-reversion-with-atr-bands-1m/README.md new file mode 100644 index 0000000..c9247b5 --- /dev/null +++ b/templates/usdcad-mean-reversion-with-atr-bands-1m/README.md @@ -0,0 +1,49 @@ +# USDCAD Mean reversion with ATR bands 1m + +This strategy implements a mean reversion approach using ATR bands for USDCAD on 1-minute candles using RandomForestClassifier. + +## Overview + +- **Pair**: USDCAD +- **Timeframe**: 1m +- **Model**: RandomForestClassifier with feature engineering focused on mean reversion with ATR bands +- **Goal**: Mean reversion strategy that identifies overbought/oversold conditions relative to ATR-based bands + +## Features Engineered + +1. **Returns**: 1, 3, 6, 12 period returns +2. **ATR for normalization and bands**: Average True Range for volatility measurement +3. **ATR-normalized candle range and close location value** (from idea) +4. **Mean reversion with ATR bands**: + - SMA 20 as midline + - Upper/lower ATR bands (SMA ± 2×ATR) + - Position within ATR bands (% of band width) + - Distance from ATR bands (normalized) + - Percentage of time price spends outside bands (mean reversion signal) +5. **Rolling volatility percentile** (from idea): Fast/slow volatility ratio, volatility percentile +6. **Distance from EMAs** (from idea): 20, 50, and 200 period EMAs +7. **Prior swing high and swing low distance** (from idea) +8. **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`: 0.0006 (6 pips) for ATR-normalized breakout +- `min_confidence`: 0.52 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. \ No newline at end of file diff --git a/templates/usdcad-mean-reversion-with-atr-bands-1m/quant.config.json b/templates/usdcad-mean-reversion-with-atr-bands-1m/quant.config.json new file mode 100644 index 0000000..338fe73 --- /dev/null +++ b/templates/usdcad-mean-reversion-with-atr-bands-1m/quant.config.json @@ -0,0 +1,28 @@ +{ + "pair": "USDCAD", + "timeframe": "1m", + "model_family": "sklearn RandomForest", + "runtime_target": "edge", + "artifact_format": "weights_bundle", + "parameters": { + "lookback": 100, + "horizon": 1, + "threshold": 0.0006, + "min_confidence": 0.52 + }, + "training_requirements": [ + "numpy", + "pandas", + "scikit-learn", + "joblib" + ], + "inference_requirements": [ + "numpy", + "pandas", + "scikit-learn", + "joblib" + ], + "symbol": "USDCAD", + "description": "USDCAD mean reversion with ATR bands strategy using RandomForestClassifier", + "disclaimer": "Educational template only. Not financial advice." +} \ No newline at end of file diff --git a/templates/usdcad-mean-reversion-with-atr-bands-1m/strategy.py b/templates/usdcad-mean-reversion-with-atr-bands-1m/strategy.py new file mode 100644 index 0000000..38f529a --- /dev/null +++ b/templates/usdcad-mean-reversion-with-atr-bands-1m/strategy.py @@ -0,0 +1,151 @@ +import numpy as np +import pandas as pd +from sklearn.ensemble import RandomForestClassifier +from sklearn.pipeline import Pipeline +from sklearn.preprocessing import StandardScaler + + +SYMBOL = "USDCAD" +MODEL_NAME = "usdcad-mean-reversion-with-atr-bands-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 and bands + 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) + + # Mean reversion with ATR bands + # Calculate ATR-based bands (similar to Bollinger Bands but with ATR) + sma_20 = c.rolling(20).mean() + upper_atr_band = sma_20 + (atr * 2.0) + lower_atr_band = sma_20 - (atr * 2.0) + + # Position within ATR bands (% of band width) + band_width = upper_atr_band - lower_atr_band + out["position_in_atr_bands"] = (c - lower_atr_band) / band_width.replace(0, np.nan) + + # Distance from ATR bands (normalized) + out["dist_to_upper_atr_band"] = (upper_atr_band - c) / atr.replace(0, np.nan) + out["dist_to_lower_atr_band"] = (c - lower_atr_band) / atr.replace(0, np.nan) + + # Percentage of time price spends outside bands (mean reversion signal) + out["pct_time_upper_band"] = (c > upper_atr_band).rolling(50).mean() + out["pct_time_lower_band"] = (c < lower_atr_band).rolling(50).mean() + + # Rolling volatility percentile (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 (from idea) + 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 (from idea) + 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() + + 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", 0.0006)) + df = _normalise(data) + feat = _features(df) + y = _labels(df["close"], feat.index, horizon, threshold) + + model = Pipeline([ + ("scaler", StandardScaler()), + ("clf", RandomForestClassifier(n_estimators=250, max_depth=7, min_samples_leaf=6, class_weight="balanced_subsample", random_state=42, n_jobs=-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", 0.52)) + 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 + }} \ No newline at end of file