Financial Time Series Analysis and Forecasting with HHT Feature Generation and Machine Learning

Applied Stochastic Models in Business and Industry

28 Pages Posted: 5 Jun 2020 Last revised: 24 Apr 2021

See all articles by Tim Leung

Tim Leung

University of Washington - Department of Applied Math

Theodore Zhao

University of Washington, Dept. of Applied Mathematics; Microsoft Corporation - Microsoft Research - Redmond

Date Written: May 11, 2020

Abstract

We present the method of complementary ensemble empirical mode decomposition (CEEMD) and Hilbert-Huang transform (HHT) for analyzing nonstationary financial time series. This noise-assisted approach decomposes any time series into a number of intrinsic mode functions, along with the corresponding instantaneous amplitudes and instantaneous frequencies. Different combinations of modes allow us to reconstruct the time series using components of different timescales. We then apply Hilbert spectral analysis to define and compute the associated instantaneous energy-frequency spectrum to illustrate the properties of various timescales embedded in the original time series. Using HHT, we generate a collection of new features and integrate them into machine learning models, such as regression tree ensemble, support vector machine (SVM), and long short-term memory (LSTM) neural network. Using empirical financial data, we compare several HHT-enhanced machine learning models in terms of forecasting performance.

Keywords: time series, signal processing, machine learning, support vector machine, long short-term memory, Hilbert-Huang transform, empirical mode decomposition

JEL Classification: C14, C41, C55

Suggested Citation

Leung, Tim and Zhao, Zhengde, Financial Time Series Analysis and Forecasting with HHT Feature Generation and Machine Learning (May 11, 2020). Applied Stochastic Models in Business and Industry, Available at SSRN: https://ssrn.com/abstract=3595914 or http://dx.doi.org/10.2139/ssrn.3595914

Tim Leung (Contact Author)

University of Washington - Department of Applied Math ( email )

Lewis Hall 217
Department of Applied Math
Seattle, WA 98195
United States

HOME PAGE: http://faculty.washington.edu/timleung/

Zhengde Zhao

University of Washington, Dept. of Applied Mathematics ( email )

Seattle, WA
United States

Microsoft Corporation - Microsoft Research - Redmond ( email )

Building 99
Redmond, WA
United States

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
833
Abstract Views
2,512
Rank
57,265
PlumX Metrics