Home > Research > Publications & Outputs > Essays on Hybrid Modeling of Machine Learning A...

Research

Electronic data

  • 2022LuoPhD.pdf

    Final published version, 3.83 MB, PDF document

    Available under license: CC BY-NC-ND: Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License

Text available via DOI:

View graph of relations

Essays on Hybrid Modeling of Machine Learning Algorithms and Financial Time Series Models

Research output: Thesis › Doctoral Thesis

Published

Standard

Essays on Hybrid Modeling of Machine Learning Algorithms and Financial Time Series Models. / Luo, Sherry.
Lancaster University, 2022. 130 p.

Research output: Thesis › Doctoral Thesis

Harvard

Luo, S 2022, 'Essays on Hybrid Modeling of Machine Learning Algorithms and Financial Time Series Models', PhD, Lancaster University. https://doi.org/10.17635/lancaster/thesis/1733

APA

Luo, S. (2022). Essays on Hybrid Modeling of Machine Learning Algorithms and Financial Time Series Models. [Doctoral Thesis, Lancaster University]. Lancaster University. https://doi.org/10.17635/lancaster/thesis/1733

Vancouver

Luo S. Essays on Hybrid Modeling of Machine Learning Algorithms and Financial Time Series Models. Lancaster University, 2022. 130 p. doi: 10.17635/lancaster/thesis/1733

Author

Luo, Sherry. / Essays on Hybrid Modeling of Machine Learning Algorithms and Financial Time Series Models. Lancaster University, 2022. 130 p.

Bibtex

@phdthesis{9fe0725ff4294ae0bbbe626446f2711b,
title = "Essays on Hybrid Modeling of Machine Learning Algorithms and Financial Time Series Models",
abstract = "This thesis attempts to model and forecast realized volatility and stock market tail risk using hybrid models integrating Machine Learning algorithms with Financial Time Series models. One of the advantages of Machine Learning approaches is that it can well approximate a wide range class of linear and nonlinear functions, forming the input-output map by learning the data rather than assuming the data generating process. Traditional Time Series models, however, focus on reproducing the stylized facts of target variables through statistical modeling. By hybriding these two types of models, we find that Machine Learning approaches well complement Financial Time Series models in variable screening, complex relationship detection and nonlinearity modeling. In addition, it is found that instead of using raw data in the Machine Learning algorithms, Financial Time Series models generate more effective features that significantly improves learning ability of those algorithms.",
author = "Sherry Luo",
year = "2022",
doi = "10.17635/lancaster/thesis/1733",
language = "English",
publisher = "Lancaster University",
school = "Lancaster University",

}

RIS

TY - BOOK

T1 - Essays on Hybrid Modeling of Machine Learning Algorithms and Financial Time Series Models

AU - Luo, Sherry

PY - 2022

Y1 - 2022

N2 - This thesis attempts to model and forecast realized volatility and stock market tail risk using hybrid models integrating Machine Learning algorithms with Financial Time Series models. One of the advantages of Machine Learning approaches is that it can well approximate a wide range class of linear and nonlinear functions, forming the input-output map by learning the data rather than assuming the data generating process. Traditional Time Series models, however, focus on reproducing the stylized facts of target variables through statistical modeling. By hybriding these two types of models, we find that Machine Learning approaches well complement Financial Time Series models in variable screening, complex relationship detection and nonlinearity modeling. In addition, it is found that instead of using raw data in the Machine Learning algorithms, Financial Time Series models generate more effective features that significantly improves learning ability of those algorithms.

AB - This thesis attempts to model and forecast realized volatility and stock market tail risk using hybrid models integrating Machine Learning algorithms with Financial Time Series models. One of the advantages of Machine Learning approaches is that it can well approximate a wide range class of linear and nonlinear functions, forming the input-output map by learning the data rather than assuming the data generating process. Traditional Time Series models, however, focus on reproducing the stylized facts of target variables through statistical modeling. By hybriding these two types of models, we find that Machine Learning approaches well complement Financial Time Series models in variable screening, complex relationship detection and nonlinearity modeling. In addition, it is found that instead of using raw data in the Machine Learning algorithms, Financial Time Series models generate more effective features that significantly improves learning ability of those algorithms.

U2 - 10.17635/lancaster/thesis/1733

DO - 10.17635/lancaster/thesis/1733

M3 - Doctoral Thesis

PB - Lancaster University

ER -