"""Accurate per-wallet P&L for Polymarket makers, from the FULL activity ledger. (read-only; touches no account and places nothing) WHY NOT /trades. Reconstructing a position from /trades alone is WRONG for exactly the wallets worth studying. Polymarket lets you SPLIT $1 of collateral into a Yes+No pair and MERGE it back, and neither is a trade -- so a maker who mints inventory instead of crossing a spread has trades that look like unexplained one-sided selling. pm_maker_study.py did this and produced $1.7M on 384 fills, which is not a real number. /activity carries every cash-affecting event: TRADE SPLIT MERGE REDEEM REWARD MAKER_REBATE YIELD so net cash flow over a closed history IS realised P&L, with no position arithmetic required at all. SIGNS. BUY -usdc, SELL +usdc, SPLIT -usdc (pay collateral, receive tokens), MERGE +usdc (return tokens, receive collateral), REDEEM +usdc (settlement). Still-open positions are valued from /positions.currentValue. SUBSIDY IS NOT THE STORY. Kalshi pays makers nothing, so income Polymarket pays for providing liquidity would not transfer to us -- but measured over six high-activity wallets it is 0.000%-0.351% of trade volume. Reported separately so it can be subtracted, but it does not change any ranking. CROSS-CHECK. /positions carries Polymarket's OWN cashPnl per open position. Two independent derivations that agree are worth far more than one that cannot be checked; `pnl_check_delta` is the disagreement and a large value means do not trust the row. """ import collections import csv import os import sys import time import requests DATA = 'https://data-api.polymarket.com' HERE = os.path.dirname(os.path.abspath(__file__)) IN_CSV = os.path.join(HERE, 'pm_maker_study.csv') OUT = os.path.join(HERE, 'pm_maker_pnl.csv') SUBSIDY = {'REWARD', 'MAKER_REBATE', 'YIELD'} def _get(url, params, tries=4): for i in range(tries): try: r = requests.get(url, params=params, timeout=30) except Exception: time.sleep(1.2 * (i + 1)); continue if r.status_code == 200: return r.json() if r.status_code == 400: return None time.sleep(1.2 * (i + 1)) return None ACTIVITY_CAP = 5400 # /activity returns HTTP 400 past roughly here def wallet_pnl(w, max_rows=ACTIVITY_CAP): """Cash-flow P&L. `capped` means the history is INCOMPLETE -- do not use it. The offset cap is not a nuisance, it is a correctness boundary. With only the most recent N events, a SELL or REDEEM whose matching purchase falls outside the window has no cost basis and reads as pure profit, so a truncated wallet's P&L is biased UPWARD without limit. That is what produced an $8.8M row on the first pass. So a wallet is only scored when its ENTIRE history fits under the cap. That biases the sample toward smaller operators -- the tradeoff is an exact number instead of a fictional one. """ cash = 0.0 subsidy = 0.0 vol = 0.0 types = collections.Counter() off = 0 capped = False while True: if off >= max_rows: capped = True break d = _get(f'{DATA}/activity', {'user': w, 'limit': 500, 'offset': off}) if d is None: # HTTP 400 -> we hit the wall, history is longer capped = True break if not d: break for a in d: t = a.get('type') try: u = float(a.get('usdcSize') or 0) except (TypeError, ValueError): continue types[t] += 1 if t in SUBSIDY: subsidy += u elif t == 'TRADE': vol += u cash += u if (a.get('side') or '').upper() == 'SELL' else -u elif t == 'SPLIT': cash -= u elif t in ('MERGE', 'REDEEM'): cash += u off += len(d) if len(d) < 500: break time.sleep(0.1) # open positions still carry value; /positions is also Polymarket's own P&L open_val = 0.0 own_pnl = 0.0 pos = _get(f'{DATA}/positions', {'user': w, 'limit': 500}) or [] for p in pos: try: open_val += float(p.get('currentValue') or 0) own_pnl += float(p.get('cashPnl') or 0) except (TypeError, ValueError): pass return { 'wallet': w, 'pnl_spread': round(cash + open_val, 2), 'pnl_subsidy': round(subsidy, 2), 'pnl_total': round(cash + open_val + subsidy, 2), 'trade_volume': round(vol), 'open_value': round(open_val, 2), 'pm_cashpnl_open': round(own_pnl, 2), 'rows': sum(types.values()), 'splits': types.get('SPLIT', 0), 'merges': types.get('MERGE', 0), 'redeems': types.get('REDEEM', 0), 'capped': int(capped), } def main(): min_fills = int(sys.argv[1]) if len(sys.argv) > 1 else 200 src = list(csv.DictReader(open(IN_CSV, encoding='utf-8'))) ws = [r for r in src if int(r['fills']) >= min_fills and float(r['maker_share']) >= 0.6] print(f'{len(ws)} maker-dominant wallets with >={min_fills} fills\n') out = [] for i, r in enumerate(ws, 1): d = wallet_pnl(r['wallet']) d['maker_share'] = r['maker_share'] d['avg_legs_per_event'] = r['avg_legs_per_event'] d['all3_event_share'] = r['all3_event_share'] d['fills_sampled'] = r['fills'] if d['capped']: print(' %2d/%d %s SKIPPED - history exceeds the offset cap' % (i, len(ws), d['wallet'][:14])) continue out.append(d) print(' %2d/%d %s spread=%12.0f subsidy=%8.0f rows=%-6d COMPLETE' % (i, len(ws), d['wallet'][:14], d['pnl_spread'], d['pnl_subsidy'], d['rows'])) out.sort(key=lambda d: -d['pnl_spread']) with open(OUT, 'w', newline='', encoding='utf-8') as fh: w_ = csv.DictWriter(fh, fieldnames=list(out[0].keys())) w_.writeheader(); w_.writerows(out) print(f'\nwrote {len(out)} -> {OUT}') prof = [d for d in out if d['pnl_spread'] > 0] print('\nprofitable on SPREAD alone: %d of %d (%.0f%%)' % (len(prof), len(out), 100 * len(prof) / max(len(out), 1))) if prof: a = sum(float(d['avg_legs_per_event']) for d in prof) / len(prof) s3 = sum(float(d['all3_event_share']) for d in prof) / len(prof) print(' their mean legs/match : %.2f (3.0 = full book like ours)' % a) print(' their share of matches all3: %.0f%%' % (100 * s3)) los = [d for d in out if d['pnl_spread'] <= 0] if los: a = sum(float(d['avg_legs_per_event']) for d in los) / len(los) print(' LOSERS mean legs/match : %.2f' % a) return 0 if __name__ == '__main__': sys.exit(main())