Data-driven measures of high-frequency trading

TL;DR

This paper introduces novel data-driven measures of high-frequency trading activity using machine learning, enabling better identification and understanding of HFT's impact on market dynamics over a decade.

Contribution

The authors develop and validate new measures of HFT activity from public data, outperforming traditional proxies and revealing HFT's effects on price discovery.

Findings

HFT measures outperform conventional proxies in capturing HFT dynamics

Liquidity-supplying HFTs enhance price discovery around earnings

Liquidity-demanding HFT strategies impede information acquisition

Abstract

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.