"""Agent 33 — GradientBoostingClassifier up/down direction model (family=ml, slug=gbm). THE ANGLE (assigned): a GradientBoostingClassifier (sklearn) that classifies "will the forward move be up or down?" from a causal technical feature vector, refit on an EXPANDING walk-forward window on PAST rows only (periodic refit), and maps the class probability p(up) into a probability-weighted position in [-1, +1]. This is the gradient-boosted-tree cousin of agent_30 (logistic) / agent_32 (MLP): shallow additive trees can pick up threshold/interaction effects (e.g. "high momentum AND low vol") a linear logit cannot, while staying a classifier (sign is the only persistent quantity here, magnitude is noise). WHY A CLASSIFIER (not a return-regressor): the per-bar *magnitude* of these curves is dominated by noise; only the SIGN of a multi-bar forward move has any persistence. The GBM targets exactly that Bernoulli up/down label and emits a calibrated-ish probability — a natural conviction: p~0.5 -> flat, p far from 0.5 -> take the side. Shallow stumps (max_depth small), few estimators, a low learning_rate and subsampling keep the additive model from carving the thin edge into noise. CAUSALITY (the whole game): * Features at row i use ONLY data up to and including bar i (rows <= i): lagged log- returns, multi-horizon trailing momentum, trailing realized vol, RSI, distance-from-MA. * The LABEL for row j is the sign of the cumulative return over bar j -> j+FWD_H, which needs close[j+FWD_H]. Sitting at decision-row i we may train ONLY on rows whose label is already realized: j + FWD_H <= i => j <= i - FWD_H. Row i's own label is NEVER used. * The GBM is refit on the EXPANDING window of those realized (X, y) pairs at most every REFIT_EVERY bars; the fitted model is frozen in between. position[i] = frozen model's p(up) at row i, mapped to a direction, then vol-targeted. Deterministic (fixed random_state, no shuffle) so signal(prefix) == signal(full)[:cut]. -> Verified by causality_ok (signal on a prefix must match signal on the full array). TUNING (split='train' only, combined A & B): shallow trees (max_depth 2) + few estimators + low learning_rate + subsample<1 so the weak edge isn't overfit; FWD_H in the forecastable band (next-bar sign is a coin-flip; multi-bar sign is the persistent quantity); WARMUP big enough that the first fit sees a real sample; conviction = tanh(GAIN*(2p-1)) with a deadband and an asymmetric short scale (both curves drift UP, so the classifier's real value is STEPPING ASIDE from declines, not fighting the drift with full shorts); then vol-targeted (cap 1.0) so the DRAWDOWN, not the raw forecast, is what we control. Refit cadence is COARSE (~40 bars) because a GBM is ~100x slower to fit than a logit and the edge is slow-moving. HONEST READ: forward-sign forecastability here is weak and a GBM does not manufacture it. The realistic, defensible win is a vol-controlled, low-drawdown book that de-risks/flips into declines — comparable PnL to long-only at a FRACTION of the ~77% buy&hold drawdown. The de-risking is the alpha, not a strong classifier. A thin/negative result is the honest result. """ import warnings import numpy as np import blindlib as bl warnings.filterwarnings("ignore") try: from sklearn.ensemble import GradientBoostingClassifier _HAVE_SK = True except Exception: # pragma: no cover - sklearn expected present _HAVE_SK = False # ---- tuned on split='train' only (interior of broad plateaus; see scans) ---- N_EST = 120 # number of boosting stages (modest; heavy shrinkage on a thin edge) MAX_DEPTH = 2 # shallow trees (stumps/pairs) -> capture interactions, resist overfit LEARN_RATE = 0.03 # low learning rate (heavy shrinkage on a weak signal) SUBSAMPLE = 0.7 # stochastic GB: subsample rows per stage -> regularize + decorrelate MIN_LEAF = 30 # large min leaf -> no carving the noise into tiny leaves WARMUP = 260 # realized (X, y) pairs required before the first fit REFIT_EVERY = 40 # expanding-window refit cadence (COARSE: GBM is slow + edge is slow) LAGS = (1, 2, 3, 5) # lagged log-return features MOM_WINS = (10, 20, 40) # multi-horizon trailing-momentum features VOL_WIN = 20 # trailing realized-vol feature window RSI_WIN = 14 # RSI feature window MA_WIN = 50 # distance-from-MA feature window FWD_H = 15 # label HORIZON: sign of cumulative return over next FWD_H bars. # next-bar sign is a coin-flip; the multi-bar sign is the persistent, # classifiable quantity. Plateau FWD ~12-20 (best at 15). DEADBAND = 0.04 # ignore |2p-1| below this (no-conviction -> flat, saves fee churn) GAIN = 3.0 # conviction gain on the centered probability 2*(p-0.5) SHORT_SCALE = 0.0 # LONG-FLAT book. Both curves drift UP, so the classifier's real # value is STEPPING ASIDE from declines, not shorting them — the # train scan is unambiguous that a short side (even partial) only # ADDS drawdown (it fights the up-drift) without improving PnL or # Sharpe. p(up)<0.5 -> FLAT, not short. The de-risking is the alpha. TARGET_VOL = 0.18 # vol-target the directional book (pure PnL/DD knob; Sharpe ~flat in it) VOL_WIN_DAYS = 45 # vol-estimation window (45 > 30 cut the worst DD on the train scan) LEV_CAP = 1.0 # never lever past fully invested -> preserve the DD cut def _build_features(c): """Causal feature matrix X (len(c) rows). Row i uses ONLY data <= i.""" n = len(c) lr = np.zeros(n) lr[1:] = np.log(c[1:] / c[:-1]) # lr[i] = return of bar ending at i (causal) csum = np.cumsum(lr) cs2 = np.cumsum(lr * lr) cols = [] # lagged returns: value at i is the return k bars ago (all <= i) for k in LAGS: f = np.zeros(n) if k < n: f[k:] = lr[: n - k] cols.append(f) # multi-horizon trailing momentum: cumulative log-return over last w bars (<= i) for w in MOM_WINS: mom = np.zeros(n) mom[w:] = csum[w:] - csum[:-w] cols.append(mom) # trailing realized vol (std of last VOL_WIN returns, <= i) vol = np.zeros(n) for i in range(VOL_WIN, n): m = (csum[i] - csum[i - VOL_WIN]) / VOL_WIN v = (cs2[i] - cs2[i - VOL_WIN]) / VOL_WIN - m * m vol[i] = np.sqrt(max(v, 0.0)) cols.append(vol) # RSI (causal, from blindlib), centered to ~[-0.5, 0.5] rsi = np.nan_to_num(bl.rsi(c, RSI_WIN), nan=50.0) / 100.0 - 0.5 cols.append(rsi) # distance from a trailing MA (causal): log(close / sma) ma = np.nan_to_num(bl.sma(c, MA_WIN), nan=c[0]) ma[ma <= 0] = 1e-9 dist = np.log(np.maximum(c, 1e-9) / ma) dist[:MA_WIN] = 0.0 cols.append(dist) X = np.column_stack(cols) return X, lr, csum def _fit(Xtr, ytr): """GradientBoostingClassifier fit on raw features (trees are scale-invariant). Returns the fitted model, or None if labels are single-class (no fit possible yet).""" if len(np.unique(ytr)) < 2: return None if _HAVE_SK: m = GradientBoostingClassifier( n_estimators=N_EST, max_depth=MAX_DEPTH, learning_rate=LEARN_RATE, subsample=SUBSAMPLE, min_samples_leaf=MIN_LEAF, random_state=0) m.fit(Xtr, ytr) return m return None def _predict_proba(m, xi): classes = list(m.classes_) if 1.0 not in classes: return 0.5 j = classes.index(1.0) return float(m.predict_proba(xi.reshape(1, -1))[0, j]) def signal(df): c = df["close"].values.astype(float) n = len(c) X, lr, csum = _build_features(c) # label[j] = 1 if cumulative return over bar j -> j+FWD_H is up, else 0. # realized (known) only as of close[j+FWD_H]. fwd = np.zeros(n) fwd[: n - FWD_H] = csum[FWD_H:] - csum[: n - FWD_H] label = (fwd > 0).astype(float) first = max(max(LAGS), max(MOM_WINS), VOL_WIN, RSI_WIN, MA_WIN) # first fully-featured row prob = np.full(n, 0.5) model = None for i in range(n): last_train = i - FWD_H # label of last_train uses close[i], realized now ntrain = last_train - first + 1 if ntrain >= WARMUP: if model is None or (i % REFIT_EVERY == 0): Xtr = X[first : last_train + 1] ytr = label[first : last_train + 1] fit = _fit(Xtr, ytr) if fit is not None: model = fit if model is not None: prob[i] = _predict_proba(model, X[i]) # probability -> bounded direction. centered conviction 2*(p-0.5) in [-1,1]; # deadband kills no-conviction bars; tanh sharpens; the short side is scaled down # (the up-drift makes full shorts a losing fight — we mainly want to step aside). conv = 2.0 * prob - 1.0 conv = np.where(np.abs(conv) < DEADBAND, 0.0, conv) direction = np.tanh(GAIN * conv) direction = np.where(direction < 0.0, direction * SHORT_SCALE, direction) direction = np.nan_to_num(direction, nan=0.0) pos = bl.vol_target(direction, df, target_vol=TARGET_VOL, vol_win_days=VOL_WIN_DAYS, leverage_cap=LEV_CAP) return np.clip(np.nan_to_num(pos, nan=0.0), -1.0, 1.0)