PythagorasGoal/scripts/research/xsec/runs/XU03.py

"""XU03 — Long-Only Top-k (Alt Selection)
MECHANISM: Low-vol / momentum LONG-ONLY top-k alt selection.
  - NOT market-neutral: goes long only the top-k alts by combined score, flat otherwise.
  - Captures alt-beta + selection effect (distinct from XS01 which is market-neutral).
  - Executable at small capital (k legs, no short book needed).

Signal: blend of momentum (z30+z90) and low-vol (-rv30) in a composite score.
  The combined signal selects alts that are trending UP and relatively stable.
  long_short=False -> long-only top-k, no short leg.

Grid (5 backtests):
  1. MOM_LO  H=10 k=5  universe=majors   — baseline long-only momentum
  2. MOM_LO  H=10 k=5  universe=all      — wider universe, more selection power
  3. COMBO   H=10 k=5  universe=majors   — blend momentum + low-vol (composite)
  4. COMBO   H=20 k=5  universe=majors   — slower rebalance, lower turnover
  5. COMBO   H=10 k=3  universe=majors   — tighter portfolio (top-3 only)

Hypothesis: long-only selection will have high corr_tp01 (market beta) but low corr_xs01
(market-neutral XS01 cancels market beta). If the composite score selects quality alts that
outperform TP01 (BTC/ETH only), it adds informational value.
"""
import sys
sys.path.insert(0, "/opt/docker/PythagorasGoal/scripts/research/xsec")
import xslib as xs
import numpy as np

print("XU03 — Long-Only Top-k (Alt Selection: Momentum + Low-Vol Composite)")
print("=" * 70)


def mom_blend(P):
    """Z-blend of 30d and 90d momentum — same signal as XS01 but long-only."""
    z30 = xs.xs_zscore(xs.past_return(P.close, 30))
    z90 = xs.xs_zscore(xs.past_return(P.close, 90))
    return np.nanmean(np.stack([z30, z90], axis=0), axis=0)


def combo_score(P):
    """Composite: momentum blend + low-vol preference.
    Selects alts that are trending up AND have lower realized volatility.
    Both components are cross-sectionally z-scored before blending.
    """
    # Momentum: 30d + 90d blend
    z30 = xs.xs_zscore(xs.past_return(P.close, 30))
    z90 = xs.xs_zscore(xs.past_return(P.close, 90))
    z_mom = np.nanmean(np.stack([z30, z90], axis=0), axis=0)

    # Low-vol: prefer stable alts (negate RV so higher = lower vol = preferred)
    rv = xs.roll_std(P.ret, 30)
    z_lvol = xs.xs_zscore(-rv)

    # Equal blend: 50% momentum + 50% low-vol
    combo = np.nanmean(np.stack([z_mom, z_lvol], axis=0), axis=0)
    return combo


# 1) Pure momentum long-only, majors universe — baseline
rep1 = xs.study_xs(
    "XU03_MOM_LO_H10k5_majors",
    mom_blend,
    universe="majors", H=10, k=5, long_short=False
)
print(xs.fmt(rep1))
print("JSON:", xs.as_json(rep1))
print()

# 2) Pure momentum long-only, all universe — tests wider selection
rep2 = xs.study_xs(
    "XU03_MOM_LO_H10k5_all",
    mom_blend,
    universe="all", H=10, k=5, long_short=False
)
print(xs.fmt(rep2))
print("JSON:", xs.as_json(rep2))
print()

# 3) Composite (mom + low-vol) long-only, majors — main hypothesis
rep3 = xs.study_xs(
    "XU03_COMBO_H10k5_majors",
    combo_score,
    universe="majors", H=10, k=5, long_short=False
)
print(xs.fmt(rep3))
print("JSON:", xs.as_json(rep3))
print()

# 4) Composite, slower rebalance H=20 — lower turnover, more patient selection
rep4 = xs.study_xs(
    "XU03_COMBO_H20k5_majors",
    combo_score,
    universe="majors", H=20, k=5, long_short=False
)
print(xs.fmt(rep4))
print("JSON:", xs.as_json(rep4))
print()

# 5) Composite, tighter k=3 — more concentrated, highest-conviction picks only
rep5 = xs.study_xs(
    "XU03_COMBO_H10k3_majors",
    combo_score,
    universe="majors", H=10, k=3, long_short=False
)
print(xs.fmt(rep5))
print("JSON:", xs.as_json(rep5))
print()

# Summary
print("=" * 70)
print("SUMMARY: All 5 configs ranked by hold-out Sharpe")
all_reps = [rep1, rep2, rep3, rep4, rep5]
ranked = sorted(all_reps, key=lambda r: r["holdout"].get("sharpe", -999), reverse=True)
for r in ranked:
    h_sh = r["holdout"].get("sharpe", 0)
    f_sh = r["full"]["sharpe"]
    c_xs01 = r["corr_xs01"]
    c_tp01 = r["corr_tp01"]
    verdict = r["marginal"].get("verdict", "N/A")
    earns = r["earns_slot"]
    print(f"  {r['name']:35s} FULL={f_sh:+.2f} HOLD={h_sh:+.2f} "
          f"corr_xs01={c_xs01:+.2f} corr_tp01={c_tp01:+.2f} "
          f"verdict={verdict} earns_slot={earns}")

# Pick best config by: earns_slot first, then hold-out > 0 + distinct, then hold-out
best = None
for r in ranked:
    if r["earns_slot"]:
        best = r
        break
if best is None:
    candidates = [r for r in ranked
                  if (r.get("corr_xs01") or 1.0) < 0.6 and r["holdout"].get("sharpe", 0) > 0]
    best = candidates[0] if candidates else ranked[0]

print()
print("BEST CONFIG:")
print(xs.fmt(best))
print("JSON:", xs.as_json(best))