05a81c5e5f
Reasoned about WHERE our edge structure fits (reflexivity+breadth+low-cost overlap) -> picked the liquid high-vol equity cohort (>$10M/day liquid AND high realized vol = reflexive story-stocks, ~87 names) = equity analog of crypto's reflexive cohort, avoiding both walls. Momentum/reversal still negative (regime+efficiency), but LOW-VOL (lottery- aversion) FITS: L/S net +0.74, OOS +0.72, CPCVmed +0.73, positive 3/4 years, LongOnly +0.33. First equity signal to survive net cost (broad test had lowvol +0.02). Theoretically sound (fade overpriced hype/lottery names in the reflexive cohort). LEAD not deploy-grade: DSR 0.28<0.5, short 3.2y data, thin cohort, short-side borrow cost unmodeled. Non-crypto, low-cost, Databento. Next: full gauntlet (bootstrap/cohort-robustness/borrow/deflation). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
100 lines
4.5 KiB
Python
100 lines
4.5 KiB
Python
#!/usr/bin/env python3
|
|
"""THE CHALLENGE: does the liquid high-volatility equity cohort fit our edge structure?
|
|
|
|
The equity analog of crypto's reflexive cohort: LIQUID (top by dollar-vol -> low cost, avoids the
|
|
small-cap wall) AND HIGH realized vol (reflexive, retail-driven, less fundamentally-anchored ->
|
|
where momentum can persist, unlike efficient large-caps). The one slice where reflexivity and
|
|
liquidity OVERLAP. Test cross-sectional momentum / reversal / low-vol AND long-only momentum
|
|
(no borrow) within this cohort, gross + net of realistic (liquid ~10bp) cost, OOS, per-year.
|
|
Reuses the already-downloaded DBEQ data (free).
|
|
"""
|
|
import math
|
|
import os
|
|
import sys
|
|
|
|
import numpy as np
|
|
|
|
sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
|
|
from equity_factor_gate import load, roll, trailing # noqa: E402
|
|
from signal_sweep import xs_weights, validate, sharpe_t # noqa: E402
|
|
import torch # noqa: E402
|
|
|
|
DEV = "cuda" if torch.cuda.is_available() else "cpu"
|
|
DV_FLOOR = 1e7 # $10M/day: liquid -> low cost (avoid the small-cap wall)
|
|
VOL_PCTILE = 0.60 # keep names above 60th pctile realized vol (the reflexive cohort)
|
|
COST_BP = 10.0 # liquid names: ~10bp round-trip (illiquidity wall avoided by construction)
|
|
|
|
|
|
def main():
|
|
insts, days, close, dvol = load()
|
|
T, N = close.shape
|
|
lc = np.log(close)
|
|
R = np.zeros((T, N)); R[1:] = lc[1:] - lc[:-1]; R = np.where(np.isfinite(R), R, 0.0)
|
|
dv30 = roll(np.mean, np.nan_to_num(dvol), 30)
|
|
vol63 = roll(np.std, R, 63)
|
|
year = (1970 + days / 365.25).astype(int)
|
|
|
|
# cohort: liquid AND high-vol (reflexive)
|
|
univ = np.zeros((T, N), bool)
|
|
for t in range(T):
|
|
liq = (dv30[t] > DV_FLOOR) & np.isfinite(close[t]) & np.isfinite(vol63[t])
|
|
e = np.where(liq)[0]
|
|
if len(e) > 50:
|
|
thr = np.quantile(vol63[t, e], VOL_PCTILE)
|
|
univ[t, e[vol63[t, e] >= thr]] = True
|
|
print(f"loaded {N} insts {T}d; cohort/day ~{int(univ.sum(1).mean())} (liquid>${DV_FLOOR/1e6:.0f}M & high-vol)")
|
|
|
|
def held_weekly(w, K=5):
|
|
a = 2.0 / (5 + 1)
|
|
for t in range(1, T):
|
|
w[t] = a * w[t] + (1 - a) * w[t - 1]
|
|
wh = w.copy(); last = 0
|
|
for t in range(T):
|
|
if t % K == 0:
|
|
last = t
|
|
wh[t] = wh[last] = w[last]
|
|
return wh
|
|
|
|
def pnl_ls(sig, net=True): # long-short market-neutral
|
|
s = sig.copy(); s[~univ] = np.nan
|
|
w = held_weekly(xs_weights(s))
|
|
g = np.sum(w[:-1] * R[1:], axis=1)
|
|
if not net:
|
|
return g
|
|
return g - np.sum(np.abs(w[1:] - w[:-1]), axis=1) * COST_BP / 1e4
|
|
|
|
def pnl_long(sig, q=0.10, net=True): # long-only top-decile (no borrow)
|
|
s = sig.copy(); s[~univ] = np.nan
|
|
w = np.zeros((T, N))
|
|
for t in range(T):
|
|
e = np.where(np.isfinite(s[t]) & univ[t])[0]
|
|
if len(e) > 20:
|
|
k = max(int(q * len(e)), 5)
|
|
top = e[np.argsort(-s[t, e])[:k]]; w[t, top] = 1.0 / k
|
|
w = held_weekly(w)
|
|
g = np.sum(w[:-1] * R[1:], axis=1)
|
|
if net:
|
|
g -= np.sum(np.abs(w[1:] - w[:-1]), axis=1) * COST_BP / 1e4
|
|
return g
|
|
|
|
# cohort equal-weight benchmark (the beta of the cohort)
|
|
ewb = np.array([R[t][univ[t - 1]].mean() if t > 0 and univ[t - 1].any() else 0.0 for t in range(T)])[1:]
|
|
|
|
T_ = lambda x: torch.tensor(x[np.isfinite(x)], device=DEV, dtype=torch.float64)
|
|
sigs = {"mom_63_skip5": trailing(lc, 63, skip=5), "mom_126_skip5": trailing(lc, 126, skip=5),
|
|
"reversal_5": -trailing(lc, 5), "lowvol_63": -vol63}
|
|
print(f"\n===== LIQUID HIGH-VOL EQUITY COHORT — cross-sectional (net {COST_BP}bp) =====")
|
|
print(f"cohort equal-weight (beta) Sharpe: {sharpe_t(T_(ewb)):+.2f}")
|
|
print(f"{'factor':>16} {'L/S gross':>9} {'L/S NET':>8} {'OOS':>6} {'CPCVmed':>8} {'DSR':>5} {'LongOnly NET':>12} | per-year(L/S net)")
|
|
for nm, sg in sigs.items():
|
|
g = pnl_ls(sg, net=False); p = pnl_ls(sg, net=True); lo = pnl_long(sg, net=True)
|
|
v = validate(p, days, 20)
|
|
py = " ".join(f"{y}:{sharpe_t(T_(p[year[1:]==y])):+.1f}" for y in range(2023, 2027) if (year[1:] == y).sum() > 40)
|
|
print(f"{nm:>16} {sharpe_t(T_(g)):>+9.2f} {v['full']:>+8.2f} {v['oos']:>+6.2f} {v['med']:>+8.2f} {v['dsr']:>5.2f} {sharpe_t(T_(lo)):>+12.2f} | {py}")
|
|
print("\nVERDICT: a factor with L/S NET full+OOS+CPCVmed>0 & DSR>0.5 in the reflexive-liquid cohort = the fit.")
|
|
print("If momentum still negative even here, the cohort doesn't rescue it (efficiency/regime, not cost).")
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|