foxhunt/scripts/surfer/crypto_cascade_reversion.py

#!/usr/bin/env python3
"""Cascade reversion — do crypto coins BOUNCE after an extreme forced-flow down-move?

Liquidation cascades are forced deleveraging that overshoots; the harvestable consequence is the
mean-reversion bounce. Binance killed the historical liquidation feed (live websocket only), so we
test the PROXY already on disk: extreme negative trailing-H return = a cascade. Pre-registered:

  formation: trailing-H log return per coin (cross-sectional)
  signal:    LONG the bottom-q fraction (biggest losers) — long-only on crashed names
  hold:      next H hours, NON-OVERLAPPING rebalance
  cost:      5 bp / leg on actual weight turnover
  two builds: raw_long (equal-weight losers, has crypto beta)
              hedged   (long losers − short equal-weight UNIVERSE basket; beta-neutral, short leg
                        is the diversified basket NOT a single coin → dodges the short-melt-up ruin
                        that killed generic XS reversal)
  KILL: net annualized SR < 0.5 OR not positive in most years (chrono) → cascade reversion closed.

LIMITATION: npz panel has close only (no volume) → cannot condition on the volume spike that
confirms a true liquidation cascade; the extreme-return tail is the proxy. Flagged, not hidden.
"""
import math
import os

import numpy as np

OUT = "data/surfer/crypto1h"
COST_BP = 5.0
SYMS = ["BTCUSDT", "ETHUSDT", "SOLUSDT", "XRPUSDT", "BNBUSDT", "DOGEUSDT", "ADAUSDT", "AVAXUSDT",
        "LINKUSDT", "LTCUSDT", "DOTUSDT", "TRXUSDT", "BCHUSDT", "ETCUSDT", "FILUSDT", "ATOMUSDT"]
HOUR_MS = 3_600_000
HOLDS = [1, 2, 4, 8, 12, 24]   # formation == hold, hours
Q = 0.20                        # bottom quintile = biggest losers


def build_panel():
    series = {}
    for s in SYMS:
        cache = f"{OUT}/{s}.npz"
        if not os.path.exists(cache):
            continue
        d = np.load(cache)
        if len(d["ts"]) > 24 * 60:
            series[s] = (d["ts"], d["close"])
    allts = sorted(set().union(*[set((ts // HOUR_MS).tolist()) for ts, _ in series.values()]))
    tindex = {t: i for i, t in enumerate(allts)}
    syms = sorted(series)
    P = np.full((len(allts), len(syms)), np.nan)
    for j, s in enumerate(syms):
        ts, c = series[s]
        for t, px in zip(ts // HOUR_MS, c):
            P[tindex[int(t)], j] = px
    yrs = np.array([1970 + int(t) // int(365.25 * 24) for t in allts])
    return P, syms, yrs


def ann(rets, per_year_factor):
    rets = np.asarray(rets)
    if len(rets) < 20 or rets.std() == 0:
        return float("nan"), float("nan")
    sr = rets.mean() / rets.std()
    t = rets.mean() / (rets.std() / math.sqrt(len(rets)))
    return sr * per_year_factor, t


def run():
    P, syms, yrs = build_panel()
    T, N = P.shape
    logP = np.log(P)
    print(f"\n===== CRYPTO CASCADE REVERSION (long the crashed names, net {COST_BP}bp/leg) =====")
    print(f"panel: {T} hours x {N} coins  years {int(yrs.min())}-{int(yrs.max())}  q={Q} (bottom quintile)")
    print("LONG bottom-q losers; hedged = long losers - short equal-wt universe basket\n")
    hdr = f"{'hold':>5} {'periods':>8} {'build':>8} {'net_SR':>8} {'t(net)':>7} {'hit%':>6} {'per-year net-SR (chrono)':>30}"
    print(hdr); print("-" * len(hdr))

    for H in HOLDS:
        pf = math.sqrt(24 * 365 / H)
        idx = np.arange(H, T - H, H)               # need t-H for formation, t+H for fwd
        raw, hed, yr_raw, yr_hed = [], [], [], []
        w_raw_prev = np.zeros(N); w_hed_prev = np.zeros(N)
        for t in idx:
            past = logP[t] - logP[t - H]
            fwd = logP[t + H] - logP[t]
            ok = np.isfinite(past) & np.isfinite(fwd)
            n_ok = int(ok.sum())
            if n_ok < 6:
                continue
            okidx = np.where(ok)[0]
            k = max(1, int(round(Q * n_ok)))
            losers = okidx[np.argsort(past[okidx])[:k]]   # most-negative trailing return
            # raw long
            w_raw = np.zeros(N); w_raw[losers] = 1.0 / k
            # hedged: long losers - short equal-weight universe basket
            w_hed = np.zeros(N); w_hed[losers] += 1.0 / k; w_hed[okidx] -= 1.0 / n_ok
            r_raw = float(np.nansum(w_raw * fwd)) - np.abs(w_raw - w_raw_prev).sum() * COST_BP / 1e4
            r_hed = float(np.nansum(w_hed * fwd)) - np.abs(w_hed - w_hed_prev).sum() * COST_BP / 1e4
            raw.append(r_raw); hed.append(r_hed)
            yr_raw.append(int(yrs[t])); yr_hed.append(int(yrs[t]))
            w_raw_prev = w_raw; w_hed_prev = w_hed
        if len(raw) < 20:
            print(f"{H:>5} (too few periods)"); continue
        for name, series, yrl in (("raw_long", raw, yr_raw), ("hedged", hed, yr_hed)):
            sr, t = ann(series, pf)
            hit = 100.0 * np.mean(np.asarray(series) > 0)
            py = {}
            for r, y in zip(series, yrl):
                py.setdefault(y, []).append(r)
            pystr = " ".join(f"{y}:{(np.mean(v)/(np.std(v)+1e-12)):+.2f}"
                             for y, v in sorted(py.items()) if len(v) >= 10)
            tag = f"{H}h" if name == "raw_long" else ""
            print(f"{tag:>5} {len(series):>8} {name:>8} {sr:>+8.2f} {t:>+7.2f} {hit:>6.1f}   {pystr}")
        print("-" * len(hdr))
    print("PASS: hedged net SR > 0.5, t>=2, positive in most years. Else cascade reversion closed.")


if __name__ == "__main__":
    run()