Data-driven measures of high-frequency trading
Factual evidence
What the source reports
Researchers trained ML models on proprietary Nasdaq data to measure high-frequency trading strategies from public stock market variables.
Inspect the evidence
- Inclusion basis
- Enterprise AI
- Publisher and source type
- arXiv cs.LG — Machine Learning · RESEARCH
- Published by source
- 7 October 2026
- Collected by OneBench
- 8 Oct 2026, 03:02 UK
- Original headline
- Data-driven measures of high-frequency trading ↗
Stored source excerpt
arXiv:2405.08101v4 Announce Type: replace-cross Abstract: Public data do not identify high-frequency trading (HFT), and standard proxies do not separate liquidity-supplying from liquidity-demanding strategies. We overcome…
Short excerpt from the collected text, not the full source. Use the source link to read it in context.
The factual summary is a OneBench synthesis, not a quotation or independent verification. Collection time is not publication time. Open the source for its full context; related reporting can share the same underlying announcement.
OneBench interpretation
Institutional assessment
So what
Machine learning enables market participants to infer hidden liquidity-supplying and liquidity-demanding high-frequency trading volumes from public market data.
Do what
Review high-frequency trading surveillance and market-microstructure models with the team responsible for quantitative trading research.