Real-Time Detection of Volatility in Liquidity Provision

  • Matt Brigida SUNY Polytechnic Institute

Abstract

Previous research has found that high-frequency traders will vary the bid or offer price rapidly overperiods of milliseconds. This is a benefit to fast traders who can time thier trades with microsecondprecision, however it is a cost to the average market participant due to increased trade execution priceuncertainty. In this analysis we attempt to construct real-time methods for determining whether theliquidity of a security is being altered by high-frequency traders. We find a four-state Markov switchingmodel identifies a state consistent with high-frequency traders affecting liquidity. Moreover, we find thisstate is positicely corrrelated with the prediction error from a deep neural network. This state can beused as a signal to delay market participant orders until the price volatility subsides. This delay wouldonly last tens of milliseconds, and so would not be noticable by the average market participant.

Downloads

Download data is not yet available.
Published
2020-12-14
How to Cite
Brigida, M. (2020). Real-Time Detection of Volatility in Liquidity Provision. Applied Finance Letters, 9, 143 - 156. https://doi.org/10.24135/afl.v9i.268
Section
Articles submitted to regular issue