Newest papers

Where Backtests and Live Trading Part Ways: Six Defects from One Intraday System

Alex Vidovich, Zivana Zerjal · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.21846 · cited by 0 works (OpenAlex) · open-access PDF

Indonesian

Backtest strategi intraday dapat mengalihkan diri dari apa yang sebenarnya dilakukan sistem langsung; dalam kasus kami, drift tidak pernah ditunjukkan dalam statistik ringkasan. Kami melaporkan enam cacat yang ditemukan saat menjalankan satu sistem ekuitas intraday AS langsung dan membandingkan hari-hari langsung dengan replay backtest mereka. Tiga berasal dari data: feed default yang membawa sebagian kecil volume pembukaan nyata, harga bersejarah yang disesuaikan untuk dividen yang pesanan langsung tidak pernah melihat, dan data yang diunduh sistem langsung tetapi backtest tidak pernah dilakukan. Dua berasal dari kode: langkah ukuran yang melebihi batas akun langsung menegakkan, dan timestamp UTC dibaca sebagai waktu New York. Satu berasal dari konfigurasi: pengaturan yang dipindahkan tetapi tidak pernah mencapai kode yang menempatkan pesanan. Untuk masing-masing kami memberikan gejala, ukuran kesalahan, penyebab dan kontrol atau yang sekarang melindungi terhadap hal itu.

Machine translation (Meta M2M100); the English original follows.

Abstract

Backtests of intraday strategies can drift away from what the live system actually does; in our case, the drift never showed in summary statistics. We report six defects found while running one intraday US equity system live and comparing its live days with their backtest replay. Three came from data: a default feed that carried a small fraction of real opening volume, historical prices adjusted for dividends that live orders never see, and data the live system downloaded but the backtest never did. Two came from code: a sizing step that exceeded a limit the live account enforces, and UTC timestamps read as New York time. One came from configuration: settings that were switched on but never reached the code that places orders. For each we give the symptom, the size of the error, the cause and the test or control that now guards against it. All six sat where two paths that should agree had drifted apart. We close with a ten-point checklist. We make no claim about whether the system is profitable.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Equity (law), Computer science, Economics, Timestamp, Limit (mathematics), Sizing

Is this paper real? This page was built from OpenAlex and arXiv records, not generated. Software can verify any reference in one call: GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.21846, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txt

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange