The Normal-Generalised Gamma-Pareto process: A novel pure-jump L\'evy process with flexible tail and jump-activity properties

TL;DR

This paper introduces a new family of pure-jump Lévy processes with independently controllable tail and jump activity, enabling exact sampling and improved financial modeling.

Contribution

The paper presents a novel self-decomposable Lévy process with separate tail and jump activity control, and demonstrates its application in stochastic volatility models with superior predictive performance.

Findings

Exact sampling of process increments at any time scale.

Enhanced predictive accuracy in stock return modeling.

Flexible control over tail behavior and jump activity.

Abstract

Pure-jump L\'evy processes are popular classes of stochastic processes which have found many applications in finance, statistics or machine learning. In this paper, we propose a novel family of self-decomposable L\'evy processes where one can control separately the tail behavior and the jump activity of the process, via two different parameters. Crucially, we show that one can sample exactly increments of this process, at any time scale; this allows the implementation of likelihood-free Markov chain Monte Carlo algorithms for (asymptotically) exact posterior inference. We use this novel process in L\'evy-based stochastic volatility models to predict the returns of stock market data, and show that the proposed class of models leads to superior predictive performances compared to classical alternatives.