Data-Driven Measures of High-Frequency Trading
Gbenga Ibikunle, Ben Moews, Dmitriy Muravyev, Khaladdin Rzayev
Abstract
We introduce data-driven measures of high-frequency trading (HFT) that distinguish between liquidity-supplying and liquidity-demanding strategies. We train machine learning models on a proprietary dataset with observed HFT activity, then apply these models to public intraday data to generate HFT measures across all U.S. stocks during 2010-2023. Our measures outperform conventional proxies, which struggle to capture the temporal dynamics of HFT. Consistent with theory, our measures respond to a quasi-exogenous speed bump introduction and a data feed upgrade. The measures help uncover the differential impact of HFT on information acquisition. Liquidity-supplying HFT improves price informativeness around earnings announcements, while liquidity-demanding HFT impedes it.
Read the AI summary, key takeaways and discussion on WOBR Quant Research.