Marked Hawkes process modeling of price dynamics and volatility estimation

Abstract

A simple Hawkes model have been developed for the price tick structure dynamics incorporating market microstructure noise and trade clustering. In this paper, the model is extended with random mark to deal with more realistic price tick structures of equities. We examine the impact of jump in price dynamics to the future movements and dependency between the jump sizes and ground intensities. We also derive the volatility formula based on stochastic and statistical methods and compare with realized volatility in simulation and empirical studies. The marked Hawkes model is useful to estimate the intraday volatility similarly in the case of simple Hawkes model.

References in corpus (3)

• Price dynamics in a Markovian limit order market
• Non-parametric kernel estimation for symmetric Hawkes processes. Application to high frequency financial data
• Modeling microstructure price dynamics with symmetric Hawkes and diffusion model using ultra-high-frequency stock data

Cited by in corpus (5)

• Modeling bid and ask price dynamics with an extended Hawkes process and its empirical applications for high-frequency stock market data
• Recurrent neural network based parameter estimation of Hawkes model on high-frequency financial data
• Neural Hawkes: Non-Parametric Estimation in High Dimension and Causality Analysis in Cryptocurrency Markets
• Self and mutually exciting point process embedding flexible residuals and intensity with discretely Markovian dynamics
• Multi-kernel property in high-frequency price dynamics under Hawkes model