High-Frequency Market Manipulation Detection with a Markov-modulated Hawkes process

TL;DR

This paper introduces a novel Markov-modulated Hawkes process model for high-frequency market manipulation detection, extending existing models to handle more complex excitation kernels and applying it to cryptocurrency data.

Contribution

It develops an expectation-maximization algorithm for parameter inference in a generalized Markov-modulated Hawkes process, enabling better detection of anomalous trading activities.

Findings

The model effectively detects suspicious trading bursts.

Numerical tests show good convergence of estimators.

Benchmarking confirms improved fit over simpler models.

Abstract

This work focuses on a self-exciting point process defined by a Hawkes-like intensity and a switching mechanism based on a hidden Markov chain. Previous works in such a setting assume constant intensities between consecutive events. We extend the model to general Hawkes excitation kernels that are piecewise constant between events. We develop an expectation-maximization algorithm for the statistical inference of the Hawkes intensities parameters as well as the state transition probabilities. The numerical convergence of the estimators is extensively tested on simulated data. Using high-frequency cryptocurrency data on a top centralized exchange, we apply the model to the detection of anomalous bursts of trades. We benchmark the goodness-of-fit of the model with the Markov-modulated Poisson process and demonstrate the relevance of the model in detecting suspicious activities.