Sequential hypothesis testing in machine learning, and crude oil price jump size detection
This work addresses jump detection in financial time series, specifically for crude oil markets, but appears incremental as it builds on existing models with machine learning enhancements.
The paper tackles the problem of detecting general jump size distributions in sequential hypothesis testing, applying it to crude oil price data, and shows that incorporating a deterministic component extracted via machine learning improves the Barndorff-Nielsen and Shephard model.
In this paper we present a sequential hypothesis test for the detection of general jump size distrubution. Infinitesimal generators for the corresponding log-likelihood ratios are presented and analyzed. 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 crude oil data set, and the deterministic component is implemented to improve the Barndorff-Nielsen and Shephard model, a commonly used stochastic model for derivative and commodity market analysis.