foxhunt/scripts/measure_passive_mm.py

#!/usr/bin/env python3
"""Measure PASSIVE market-making economics on ES MBP-10 (markout / adverse selection).

Companion to scripts/measure_ofi_ic.py. The OFI study showed a spread-CROSSING
directional strategy is structurally unprofitable (predicted move ~0.01-0.06 ticks
vs 1-tick cost). The exploitable structure (OFI→impact, R²~0.5-0.7) lives in the
spread, capturable only by PROVIDING liquidity. This harness measures whether
earning the spread is viable after adverse selection.

Method (standard market-making markout / adverse-selection study):
  * Decode clean MBP-10; maintain best bid/ask/mid from levels[0].
  * Each TRADE (action='T') fills a hypothetical PASSIVE order at the touch:
      - side=ASK (sell aggressor, hits bid)  -> we BUY  at bid  (pos=+1, long)
      - side=BID (buy aggressor, lifts ask)  -> we SELL at ask  (pos=-1, short)
    (optimistic: assumes we win the queue on every trade — gives the UPPER BOUND
     per-fill economics; if even this is unprofitable, passive MM is dead.)
  * Per fill, PnL(Δ) in ticks = pos·(mid_{t+Δ} − fill_px)/tick − fee
                              = half_spread (≈0.5 tick) + markout − fee
    markout = pos·(mid_{t+Δ} − mid_t)  (NEGATIVE = adverse selection).
  * Viable iff half_spread + markout − fee > 0.
  * OFI-CONDITIONING: split fills by whether recent OFI agrees with our position
    (long & OFI>0, or short & OFI<0). If OFI-aligned fills have far better markout,
    OFI-conditioned quoting (rest only on the favorable side) is the real strategy —
    using the tiny OFI signal for adverse-selection AVOIDANCE, not for crossing.

Usage:
  python3 scripts/measure_passive_mm.py <file.dbn.zst> [--n-cap N] [--fee-ticks F] [--ofi-window-sec W]
  python3 scripts/measure_passive_mm.py --self-test
"""
import argparse
import sys
import time

import numpy as np

TICK = 0.25
TICK_USD = 12.50
PX_SCALE = 1e9


def compute_ofi(bid_px, bid_sz, ask_px, ask_sz):
    """Best-level OFI per consecutive event (Cont-Kukanov-Stoikov). len-1, aligned to n>=1."""
    pb_n, pb_p = bid_px[1:], bid_px[:-1]
    qb_n, qb_p = bid_sz[1:].astype(np.float64), bid_sz[:-1].astype(np.float64)
    pa_n, pa_p = ask_px[1:], ask_px[:-1]
    qa_n, qa_p = ask_sz[1:].astype(np.float64), ask_sz[:-1].astype(np.float64)
    e_bid = qb_n * (pb_n >= pb_p) - qb_p * (pb_n <= pb_p)
    e_ask = qa_p * (pa_n >= pa_p) - qa_n * (pa_n <= pa_p)
    return e_bid + e_ask


def self_test():
    # sell aggressor (agg=-1) → passive BUY at bid; bid=100 ask=100.25 mid=100.125;
    # future mid 100.25 → markout +0.5 tick, half_spread +0.5 tick, net +1.0 tick.
    bid, ask = 100.0, 100.25
    mid = (bid + ask) / 2
    pos = +1  # passive buy
    fill_px = bid
    mid_fut = 100.25
    half = pos * (mid - fill_px)
    markout = pos * (mid_fut - mid)
    net_ticks = pos * (mid_fut - fill_px) / TICK
    assert abs(half / TICK - 0.5) < 1e-9, half
    assert abs(markout / TICK - 0.5) < 1e-9, markout
    assert abs(net_ticks - 1.0) < 1e-9, net_ticks
    print(f"passive-MM self-test PASS: half={half/TICK:.2f}t markout={markout/TICK:.2f}t net={net_ticks:.2f}t")
    return 0


def decode(path, n_cap):
    import zstandard
    import databento_dbn as d
    ts = np.zeros(n_cap, np.int64)
    bpx = np.zeros(n_cap, np.int64); apx = np.zeros(n_cap, np.int64)
    bsz = np.zeros(n_cap, np.int64); asz = np.zeros(n_cap, np.int64)
    inst = np.zeros(n_cap, np.int32)
    is_trade = np.zeros(n_cap, np.bool_)
    agg = np.zeros(n_cap, np.int8)   # +1 buy-aggressor(side=BID), -1 sell-aggressor(side=ASK)
    dec = d.DBNDecoder(); dctx = zstandard.ZstdDecompressor()
    i = 0; t0 = time.time(); done = False
    with open(path, "rb") as fh:
        reader = dctx.stream_reader(fh)
        while not done:
            chunk = reader.read(1 << 22)
            if not chunk:
                break
            dec.write(chunk)
            for rec in dec.decode():
                if "MBP10" not in type(rec).__name__:
                    continue
                l0 = rec.levels[0]
                ts[i] = rec.ts_event
                bpx[i] = l0.bid_px; apx[i] = l0.ask_px
                bsz[i] = l0.bid_sz; asz[i] = l0.ask_sz
                inst[i] = rec.instrument_id
                a = str(rec.action); s = str(rec.side)
                if a.endswith("TRADE") or a == "T":
                    is_trade[i] = True
                    if s.endswith("BID") or s == "B":
                        agg[i] = 1
                    elif s.endswith("ASK") or s == "A":
                        agg[i] = -1
                i += 1
                if i >= n_cap:
                    done = True
                    break
    dt = time.time() - t0
    return ts[:i], bpx[:i], apx[:i], bsz[:i], asz[:i], inst[:i], is_trade[:i], agg[:i], dt


def analyze(path, n_cap, fee_ticks, ofi_window_sec):
    ts, bpx, apx, bsz, asz, inst, is_trade, agg, dt = decode(path, n_cap)
    n = len(ts)
    ids, cnts = np.unique(inst, return_counts=True)
    dom = ids[cnts.argmax()]
    m = inst == dom
    ts, bpx, apx, bsz, asz, is_trade, agg = ts[m], bpx[m], apx[m], bsz[m], asz[m], is_trade[m], agg[m]
    valid = (bpx > 0) & (apx > 0) & (bpx < apx)
    ts, bpx, apx, bsz, asz, is_trade, agg = (a[valid] for a in (ts, bpx, apx, bsz, asz, is_trade, agg))
    mid = (bpx + apx) / 2.0 / PX_SCALE
    print(f"\n=== {path.split('/')[-1]} ===")
    print(f"decoded {n} events in {dt:.1f}s | dominant={dom} → {valid.sum()} clean front-month events")

    # event-level OFI (aligned to events 1..), prepend 0 for event 0
    ofi = np.empty(len(ts)); ofi[0] = 0.0
    ofi[1:] = compute_ofi(bpx, bsz, apx, asz)
    cum_ofi = np.cumsum(ofi)

    # passive fills = trades with a known aggressor
    fill = is_trade & (agg != 0)
    fi = np.flatnonzero(fill)
    pos = (-agg[fi]).astype(np.float64)          # passive position: opposite the aggressor
    fill_px = np.where(pos > 0, bpx[fi], apx[fi]) / PX_SCALE
    mid_fill = mid[fi]
    half_ticks = pos * (mid_fill - fill_px) / TICK
    nbuy = int((pos > 0).sum()); nsell = int((pos < 0).sum())
    print(f"passive fills: {len(fi)} (buy={nbuy} sell={nsell}) | "
          f"avg half-spread earned = {half_ticks.mean():.3f} ticks (${half_ticks.mean()*TICK_USD:.2f})")

    # OFI in the window before each fill (adverse-selection avoidance signal)
    w_ns = int(ofi_window_sec * 1e9)
    j0 = np.searchsorted(ts, ts[fi] - w_ns, side="left")
    ofi_w = cum_ofi[fi] - cum_ofi[j0]
    aligned = np.sign(ofi_w) == np.sign(pos)     # OFI agrees with our passive direction
    print(f"OFI-window={ofi_window_sec}s | OFI-aligned fills: {100*aligned.mean():.1f}%  "
          f"fee={fee_ticks} ticks/side (${fee_ticks*TICK_USD:.2f})")

    horizons = [0.1, 1.0, 5.0, 10.0, 60.0]
    print(f"\nMARKOUT (ticks) and NET per-fill PnL = half_spread + markout − fee")
    print(f"{'Δ(s)':>6} {'markout':>9} {'net_all':>9} {'net_$':>8} {'net_aligned':>12} {'net_adverse':>12} {'sel_$/fill':>11}")
    rows = []
    for d_s in horizons:
        idx2 = np.searchsorted(ts, ts[fi] + int(d_s * 1e9), side="left")
        idx2 = np.clip(idx2, 0, len(mid) - 1)
        mid_fut = mid[idx2]
        markout = pos * (mid_fut - mid_fill) / TICK
        net = half_ticks + markout - fee_ticks
        net_aligned = net[aligned].mean() if aligned.any() else float("nan")
        net_adverse = net[~aligned].mean() if (~aligned).any() else float("nan")
        # "selective" MM: only take OFI-aligned fills
        sel_usd = (net[aligned].mean() * TICK_USD) if aligned.any() else float("nan")
        rows.append((d_s, markout.mean(), net.mean()))
        print(f"{d_s:>6} {markout.mean():>9.4f} {net.mean():>9.4f} {net.mean()*TICK_USD:>7.2f}$ "
              f"{net_aligned:>12.4f} {net_adverse:>12.4f} {sel_usd:>10.2f}$")

    print("\nINTERPRETATION:")
    print("  net_all > 0  → naive passive MM (quote both sides at touch) is viable at that horizon.")
    print("  net_aligned >> net_adverse → OFI-conditioned quoting (rest only on the favorable")
    print("     side / pull the adverse side) converts the tiny OFI signal into MM edge.")
    print("  net_all < 0 but net_aligned > 0 → naive MM loses, but SELECTIVE OFI-driven MM works.")
    return rows


def main():
    ap = argparse.ArgumentParser()
    ap.add_argument("file", nargs="?")
    ap.add_argument("--n-cap", type=int, default=8_000_000)
    ap.add_argument("--fee-ticks", type=float, default=0.1, help="per-side fee in ticks (~$1.25=0.1t)")
    ap.add_argument("--ofi-window-sec", type=float, default=1.0)
    ap.add_argument("--self-test", action="store_true")
    args = ap.parse_args()
    if args.self_test:
        return self_test()
    if not args.file:
        ap.error("file required (or --self-test)")
    analyze(args.file, args.n_cap, args.fee_ticks, args.ofi_window_sec)
    return 0


if __name__ == "__main__":
    sys.exit(main())