Energy commodity price forecasting with deep multiple kernel learning

Shian-Chang Huang, Cheng Feng Wu

Research output: Contribution to journalArticle

Abstract

Oil is an important energy commodity. The difficulties of forecasting oil prices stem from the nonlinearity and non-stationarity of their dynamics. However, the oil prices are closely correlated with global financial markets and economic conditions, which provides us with sufficient information to predict them. Traditional models are linear and parametric, and are not very effective in predicting oil prices. To address these problems, this study developed a new strategy. Deep (or hierarchical) multiple kernel learning (DMKL) was used to predict the oil price time series. Traditional methods from statistics and machine learning usually involve shallow models; however, they are unable to fully represent complex, compositional, and hierarchical data features. This explains why traditional methods fail to track oil price dynamics. This study aimed to solve this problem by combining deep learning and multiple kernel machines using information from oil, gold, and currency markets. DMKL is good at exploiting multiple information sources. It can effectively identify the relevant information and simultaneously select an apposite data representation. The kernels of DMKL were embedded in a directed acyclic graph (DAG), which is a deep model and efficient at representing complex and compositional data features. This provided a solid foundation for extracting the key features of oil price dynamics. By using real data for empirical testing, our new system robustly outperformed traditional models and significantly reduced the forecasting errors.

Original languageEnglish
Article number3029
JournalEnergies
Volume11
Issue number11
DOIs
Publication statusPublished - 2018 Nov 1

Fingerprint

Forecasting
kernel
Energy
Compositional Data
Kernel Machines
Hierarchical Data
Predict
Nonstationarity
Learning
Oils
Currency
Directed Acyclic Graph
Financial Markets
Gold
Model
Learning systems
Time series
Machine Learning
Statistics
Economics

All Science Journal Classification (ASJC) codes

  • Renewable Energy, Sustainability and the Environment
  • Energy Engineering and Power Technology
  • Energy (miscellaneous)
  • Control and Optimization
  • Electrical and Electronic Engineering

Cite this

@article{ce5439411c374b26bfc864d749434f93,
title = "Energy commodity price forecasting with deep multiple kernel learning",
abstract = "Oil is an important energy commodity. The difficulties of forecasting oil prices stem from the nonlinearity and non-stationarity of their dynamics. However, the oil prices are closely correlated with global financial markets and economic conditions, which provides us with sufficient information to predict them. Traditional models are linear and parametric, and are not very effective in predicting oil prices. To address these problems, this study developed a new strategy. Deep (or hierarchical) multiple kernel learning (DMKL) was used to predict the oil price time series. Traditional methods from statistics and machine learning usually involve shallow models; however, they are unable to fully represent complex, compositional, and hierarchical data features. This explains why traditional methods fail to track oil price dynamics. This study aimed to solve this problem by combining deep learning and multiple kernel machines using information from oil, gold, and currency markets. DMKL is good at exploiting multiple information sources. It can effectively identify the relevant information and simultaneously select an apposite data representation. The kernels of DMKL were embedded in a directed acyclic graph (DAG), which is a deep model and efficient at representing complex and compositional data features. This provided a solid foundation for extracting the key features of oil price dynamics. By using real data for empirical testing, our new system robustly outperformed traditional models and significantly reduced the forecasting errors.",
author = "Shian-Chang Huang and Wu, {Cheng Feng}",
year = "2018",
month = "11",
day = "1",
doi = "10.3390/en11113029",
language = "English",
volume = "11",
journal = "Energies",
issn = "1996-1073",
publisher = "Multidisciplinary Digital Publishing Institute (MDPI)",
number = "11",

}

Energy commodity price forecasting with deep multiple kernel learning. / Huang, Shian-Chang; Wu, Cheng Feng.

In: Energies, Vol. 11, No. 11, 3029, 01.11.2018.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Energy commodity price forecasting with deep multiple kernel learning

AU - Huang, Shian-Chang

AU - Wu, Cheng Feng

PY - 2018/11/1

Y1 - 2018/11/1

N2 - Oil is an important energy commodity. The difficulties of forecasting oil prices stem from the nonlinearity and non-stationarity of their dynamics. However, the oil prices are closely correlated with global financial markets and economic conditions, which provides us with sufficient information to predict them. Traditional models are linear and parametric, and are not very effective in predicting oil prices. To address these problems, this study developed a new strategy. Deep (or hierarchical) multiple kernel learning (DMKL) was used to predict the oil price time series. Traditional methods from statistics and machine learning usually involve shallow models; however, they are unable to fully represent complex, compositional, and hierarchical data features. This explains why traditional methods fail to track oil price dynamics. This study aimed to solve this problem by combining deep learning and multiple kernel machines using information from oil, gold, and currency markets. DMKL is good at exploiting multiple information sources. It can effectively identify the relevant information and simultaneously select an apposite data representation. The kernels of DMKL were embedded in a directed acyclic graph (DAG), which is a deep model and efficient at representing complex and compositional data features. This provided a solid foundation for extracting the key features of oil price dynamics. By using real data for empirical testing, our new system robustly outperformed traditional models and significantly reduced the forecasting errors.

AB - Oil is an important energy commodity. The difficulties of forecasting oil prices stem from the nonlinearity and non-stationarity of their dynamics. However, the oil prices are closely correlated with global financial markets and economic conditions, which provides us with sufficient information to predict them. Traditional models are linear and parametric, and are not very effective in predicting oil prices. To address these problems, this study developed a new strategy. Deep (or hierarchical) multiple kernel learning (DMKL) was used to predict the oil price time series. Traditional methods from statistics and machine learning usually involve shallow models; however, they are unable to fully represent complex, compositional, and hierarchical data features. This explains why traditional methods fail to track oil price dynamics. This study aimed to solve this problem by combining deep learning and multiple kernel machines using information from oil, gold, and currency markets. DMKL is good at exploiting multiple information sources. It can effectively identify the relevant information and simultaneously select an apposite data representation. The kernels of DMKL were embedded in a directed acyclic graph (DAG), which is a deep model and efficient at representing complex and compositional data features. This provided a solid foundation for extracting the key features of oil price dynamics. By using real data for empirical testing, our new system robustly outperformed traditional models and significantly reduced the forecasting errors.

UR - http://www.scopus.com/inward/record.url?scp=85057469432&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85057469432&partnerID=8YFLogxK

U2 - 10.3390/en11113029

DO - 10.3390/en11113029

M3 - Article

VL - 11

JO - Energies

JF - Energies

SN - 1996-1073

IS - 11

M1 - 3029

ER -