Skip to content
All library documents

Modeling Long-Range Trading Activity and Volatility with Fractal Point Processes

Article arXiv papers · Author: V. Gontis et al.
Read the original

Summary

This document proposes a stochastic model for trading activity built from a fractal point process driven by a nonlinear stochastic differential equation. The model is adjusted to financial-market trading data, with the aim of capturing statistical features of the timing and frequency of trades. It is presented as a way to represent persistent structure in activity rather than treating trades as independent events.

The reported comparison is that the model reproduces the observed probability distribution and power spectral density of stock-market trading activity. The authors also introduce a simple stochastic relationship between trading activity and returns, then use numerical calculations to reproduce long-range memory properties in volatility. The text gives no details about the data, estimation procedure, out-of-sample performance, or predictive usefulness for trading. Its evidence concerns reproduction of statistical properties, so the model’s value for forecasting or execution decisions cannot be determined from this description alone.

Key ideas

  • The proposed model represents trading activity as a fractal point process driven by a nonlinear stochastic differential equation.
  • The model is adjusted to empirical financial trading activity.
  • It is reported to reproduce observed activity distributions and power spectral density in stock markets.
  • A stochastic link between trading activity and returns is used to model persistent volatility properties.
  • The document reports statistical reproduction, but does not establish forecasting or trading performance.

Tags

StatisticsVolatilityEquitiesMarket microstructure
Full text
# Modeling long-range memory trading activity by stochastic differential equations


# Modeling long-range memory trading activity by stochastic differential equations









We propose a model of fractal point process driven by the nonlinear stochastic differential equation. The model is adjusted to the empirical data of trading activity in financial markets. This reproduces the probability distribution function and power spectral density of trading activity observed in the stock markets. We present a simple stochastic relation between the trading activity and return, which enables us to reproduce long-range memory statistical properties of volatility by numerical calculations based on the proposed fractal point process.

Shown in full with attribution under the source's licence. Licence: abstract CC0

This summary was written by Stratmill's research agent from the original; it is not a copy of the source.