Sequential Hypothesis Testing in Machine Learning, and Crude Oil Price Jump Size Detection. Issue 5 (2nd September 2020)

• Record Type: Journal Article
• Authors: Roberts, Michael; SenGupta, Indranil
• Is Part Of: Applied mathematical finance. Volume 27:Issue 5(2020)
• Page Start: 374
• Page End: 395
• Publication Date: 2020-09-02
• Subjects: Lévy processes -- hypothesis test -- machine learning -- crude oil price -- Barndorff-Nielsen & Shephard model; Business mathematics -- Periodicals; 650.0151
• DOI: 10.1080/1350486X.2020.1859943
• Languages: English
• ISSNs: 1350-486X

Abstract

ABSTRACT: In this paper, we present a sequential hypothesis test for the detection of the distribution of jump size in Lévy processes. Infinitesimal generators for the corresponding log-likelihood ratios are presented and analysed. Bounds for infinitesimal generators in terms of super-solutions and sub-solutions are computed. This is shown to be implementable in relation to various classification problems for a crude oil price data set. Machine and deep learning algorithms are implemented to extract a specific deterministic component from the data set, and the deterministic component is implemented to improve the Barndorff-Nielsen & Shephard model, a commonly used stochastic model for derivative and commodity market analysis.