Saved in:
Bibliographic Details
Main Authors: Ibikunle, G., Moews, B., Muravyev, D., Rzayev, K.
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2405.08101
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916658463899648
author Ibikunle, G.
Moews, B.
Muravyev, D.
Rzayev, K.
author_facet Ibikunle, G.
Moews, B.
Muravyev, D.
Rzayev, K.
contents High-frequency trading (HFT) accounts for almost half of equity trading volume, yet it is not identified in public data. We develop novel data-driven measures of HFT activity that separate strategies that supply and demand liquidity. We train machine learning models to predict HFT activity observed in a proprietary dataset using concurrent public intraday data. Once trained on the dataset, these models generate HFT measures for the entire U.S. stock universe from 2010 to 2023. Our measures outperform conventional proxies, which struggle to capture HFT's time dynamics. We further validate them using shocks to HFT activity, including latency arbitrage, exchange speed bumps, and data feed upgrades. Finally, our measures reveal how HFT affects fundamental information acquisition. Liquidity-supplying HFTs improve price discovery around earnings announcements while liquidity-demanding strategies impede it.
format Preprint
id arxiv_https___arxiv_org_abs_2405_08101
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Data-driven measures of high-frequency trading
Ibikunle, G.
Moews, B.
Muravyev, D.
Rzayev, K.
Computational Finance
Machine Learning
91G15, 62P20
High-frequency trading (HFT) accounts for almost half of equity trading volume, yet it is not identified in public data. We develop novel data-driven measures of HFT activity that separate strategies that supply and demand liquidity. We train machine learning models to predict HFT activity observed in a proprietary dataset using concurrent public intraday data. Once trained on the dataset, these models generate HFT measures for the entire U.S. stock universe from 2010 to 2023. Our measures outperform conventional proxies, which struggle to capture HFT's time dynamics. We further validate them using shocks to HFT activity, including latency arbitrage, exchange speed bumps, and data feed upgrades. Finally, our measures reveal how HFT affects fundamental information acquisition. Liquidity-supplying HFTs improve price discovery around earnings announcements while liquidity-demanding strategies impede it.
title Data-driven measures of high-frequency trading
topic Computational Finance
Machine Learning
91G15, 62P20
url https://arxiv.org/abs/2405.08101