☆ 4.7 Article

Portfolios with return and volatility prediction for the energy stock market

ENERGY (2023)

Related references

Note: Only part of the references are listed.

Article Thermodynamics

Forecasting the crude oil prices with an EMD-ISBM-FNN model

Tianhui Fang et al.

Summary: This paper introduces an improved slope-based method (ISBM) based on empirical mode decomposition (EMD) and feed-forward neural network (FNN) method for forecasting crude oil prices. By decomposing the time series into intrinsic mode functions (IMFs) and residuals, and training and integrating them using the FNN model, the proposed EMD-ISBM-FNN model achieves the best forecasting performance.

ENERGY (2023)

Add to Collection

Article Business, Finance

Machine learning in the Chinese stock market

Markus Leippold et al.

Summary: This study contributes to the empirical asset pricing literature in the Chinese stock market by utilizing various machine learning algorithms to build and analyze a comprehensive set of return prediction factors. The findings suggest that liquidity is the most important predictor and the dominance of retail investors positively affects short-term predictability. The predictability of large stocks and state-owned enterprises in the Chinese market over longer horizons is higher compared to the US market.

JOURNAL OF FINANCIAL ECONOMICS (2022)

Add to Collection

Article Economics

The asymmetric effects of oil price shocks on the US stock market

Sajjadur Rahman

Summary: In this paper, the authors investigate the asymmetric relation between the price of crude oil and U.S. aggregate real stock returns. They find that aggregate returns respond asymmetrically to positive and negative oil price shocks, and oil price volatility plays a major role in these asymmetries by having a negative effect on stock returns.

ENERGY ECONOMICS (2022)

Add to Collection

Article Thermodynamics

Forecasting energy prices using a novel hybrid model with variational mode decomposition

Yu Lin et al.

Summary: This paper proposes a novel decomposition-ensemble model that combines econometric and artificial intelligence methods for accurately predicting energy prices. Experiments demonstrate the effectiveness and reliability of the model.

ENERGY (2022)

Add to Collection

Article Thermodynamics

Crude oil time series prediction model based on LSTM network with chaotic Henry gas solubility optimization

Aytac Altan et al.

Summary: A new crude oil price prediction model is proposed, incorporating LSTM, technical indicators, and CHGSO technique to address the chaotic and nonlinear characteristics of crude oil time series. Features based on trend, momentum, and volatility indicators are utilized, selected by an optimization algorithm based on chaotic map, successfully coping with the chaoticity and nonlinear dynamics of crude oil time series.

ENERGY (2022)

Add to Collection

Article Energy & Fuels

A novel hybrid method for oil price forecasting with ensemble thought

Xinsheng Ding et al.

Summary: Crude oil, as a globally hard currency, plays a significant role in various aspects of the world. However, predicting oil prices is challenging due to their volatility, uncertainty, and complexity. In this study, an advanced hybrid method that combines Random Forest (RF), XGBoost (XGB), and LightGBM (LGBM) models is proposed for accurate and robust forecasting of crude oil prices. The results demonstrate that the hybrid method outperforms other individual methods in terms of Directional Accuracy (DA) and errors.

ENERGY REPORTS (2022)

Add to Collection

Article Computer Science, Artificial Intelligence

Deep learning for volatility forecasting in asset management

Alessio Petrozziello et al.

Summary: In this study, the profitability of a deep LSTM Neural Network for forecasting stock market volatility is investigated. The results demonstrate the superiority of the LSTM over traditional parametric models in predicting high volatility.

SOFT COMPUTING (2022)

Add to Collection

Article Environmental Studies

Exploring the influence of the main factors on the crude oil price volatility: An analysis based on GARCH-MIDAS model with Lasso approach

Jing Zhao

Summary: This paper comprehensively explores various influencing factors of crude oil price volatility and uses multi-factor models to predict oil prices. The findings show that multi-factor models have better prediction performance than single-factor models. Supply and demand, inventories, US dollar exchange rate, and geopolitical risk are important factors affecting oil price volatility, while the impact of alternative energy on oil price fluctuations is relatively minor.

RESOURCES POLICY (2022)

Add to Collection

Article Environmental Studies

Predicting the changes in the WTI crude oil price dynamics using machine learning models

Hasraddin Guliyev et al.

Summary: This study uses a monthly dataset from 1991 to 2021 to predict the dynamics of West Texas Intermediate (WTI) oil prices. Advanced machine learning models are employed and compared, with XgBoost and Random Forest models performing the best. The study also evaluates and interprets the models using statistical tests and SHAP values. The empirical findings demonstrate the successful and accurate prediction of WTI crude oil price trends by machine learning models.

RESOURCES POLICY (2022)

Add to Collection

Article Computer Science, Artificial Intelligence

Mean-variance portfolio optimization with deep learning based-forecasts for cointegrated stocks

Juan Du

Summary: This study introduces a new MV model that utilizes cointegrated stocks to construct stationary portfolios, and predicts expected returns using machine learning models. The results show that the portfolio built based on this model generates significant profits in both Chinese and US stock markets, with the attention-based LSTM network outperforming traditional machine learning models in predicting spread returns and selecting pairs of cointegrated stocks.

EXPERT SYSTEMS WITH APPLICATIONS (2022)

Add to Collection

Article Business, Finance

A novel two-stage method for well-diversified portfolio construction based on stock return prediction using machine learning

Wei Chen et al.

Summary: The paper proposes a diversified portfolio selection method based on stock prediction, which reduces the risk of losses for investors and improves returns.

NORTH AMERICAN JOURNAL OF ECONOMICS AND FINANCE (2022)

Add to Collection

Article Computer Science, Artificial Intelligence

Robust mean-risk portfolio optimization using machine learning-based trade-off parameter

Liangyu Min et al.

Summary: The paper proposes hybrid robust portfolio models under ellipsoidal uncertainty sets, introduces a trade-off parameter for adjusting portfolio optimism level, and uses machine learning algorithms for evaluation and forecasting. Experimental results demonstrate the effectiveness and robustness of the proposed portfolios.

APPLIED SOFT COMPUTING (2021)

Add to Collection

Article Computer Science, Artificial Intelligence

Mean-variance portfolio optimization using machine learning-based stock price prediction

Wei Chen et al.

Summary: The success of portfolio construction relies on future stock market performance, with recent advances in machine learning offering significant opportunities. This study introduces a novel approach that combines machine learning for stock prediction and the MV model for portfolio selection, showing superior results in returns and risks compared to traditional methods.

APPLIED SOFT COMPUTING (2021)

Add to Collection

Article Computer Science, Artificial Intelligence

Portfolio optimization with return prediction using deep learning and machine learning

Yilin Ma et al.

Summary: Integrating return prediction of traditional time series models in portfolio formation can improve the performance of original portfolio optimization model. Since machine learning and deep learning models have shown overwhelming superiority than time series models, this paper combines return prediction in portfolio formation with two machine learning models, i.e., random forest (RF) and three deep learning models, i.e., LSTM neural network, deep multilayer perceptron (DMLP) and convolutional neural network. Experiment results indicate that RF model performs the best in return prediction, recommending investors to utilize this model for daily trading investment.

EXPERT SYSTEMS WITH APPLICATIONS (2021)

Add to Collection

Article Management

Big data and portfolio optimization: A novel approach integrating DEA with multiple data sources

Zhongbao Zhou et al.

Summary: This study focuses on stock selection and investment weight formulation, designing a stock selection scheme integrating DEA and multiple data sources, and using SVM to predict stock price movements, resulting in a more optimal portfolio optimization model. Empirical results demonstrate that the proposed scheme can enhance the performance of all investment strategies and outperform traditional strategies.

OMEGA-INTERNATIONAL JOURNAL OF MANAGEMENT SCIENCE (2021)

Add to Collection

Article Economics

Which clean energy sectors are attractive? A portfolio diversification perspective

Wei Kuang

Summary: Clean energy stocks exhibit significant variations in risk and return, generally underperforming but outperforming dirty energy stocks. For investors, the minimum tail risk strategy is preferable over the minimum variance strategy, while an index tracking developers and operators of renewable energy projects offers optimal risk-adjusted returns for investors with moderate risk tolerance.

ENERGY ECONOMICS (2021)

Add to Collection

Article Business, Finance

Empirical asset pricing via machine learning: evidence from the European stock market

Wolfgang Drobetz et al.

Summary: This study evaluates the predictive performance of machine learning methods in forecasting European stock returns, finding that interactions and nonlinear effects can improve accuracy. Different machine learning models show substantial variation in statistical predictive performance, with neural networks performing best. The economic profitability of machine learning models also varies significantly, with neural networks producing the best results.

JOURNAL OF ASSET MANAGEMENT (2021)

Add to Collection

Article Business, Finance

Do crude oil futures still fuel portfolio performance?

Anja Vinzelberg et al.

Summary: Motivated by changes in crude oil markets, this study examines the impact of crude oil futures on investment portfolios. The findings suggest that crude oil futures have limited benefits for investors.

REVIEW OF FINANCIAL ECONOMICS (2021)

Add to Collection

Article Thermodynamics

Best-case scenario robust portfolio for energy stock market

Chen Chen et al.

ENERGY (2020)

Add to Collection

Article Business, Finance

Do the crude oil futures of the Shanghai International Energy Exchange improve asset allocation of Chinese petrochemical-related stocks?

Fei Lv et al.

INTERNATIONAL REVIEW OF FINANCIAL ANALYSIS (2020)

Add to Collection

Article Business, Finance

Empirical Asset Pricing via Machine Learning

Shihao Gu et al.

REVIEW OF FINANCIAL STUDIES (2020)

Add to Collection

Article Business, Finance

Portfolio models with return forecasting and transaction costs

Jing-Rung Yu et al.

INTERNATIONAL REVIEW OF ECONOMICS & FINANCE (2020)

Add to Collection

Article Computer Science, Interdisciplinary Applications

Realized performance of robust portfolios: Worst-case Omega vs. CVaR-related models

Jing-Rung Yu et al.

COMPUTERS & OPERATIONS RESEARCH (2019)

Add to Collection

Article Thermodynamics

Portfolio optimization of energy communities to meet reductions in costs and emissions

Andreas Fleischhacker et al.

ENERGY (2019)

Add to Collection

Article Computer Science, Artificial Intelligence

Combining Principal Component Analysis, Discrete Wavelet Transform and XGBoost to trade in the financial markets

Joao Nobre et al.

EXPERT SYSTEMS WITH APPLICATIONS (2019)

Add to Collection

Article Computer Science, Artificial Intelligence

Decision-making for financial trading: A fusion approach of machine learning and portfolio selection

Felipe Dias Paiva et al.

EXPERT SYSTEMS WITH APPLICATIONS (2019)

Add to Collection

Article Thermodynamics

Effect of increased building-integrated renewable energy on building energy portfolio and energy flows in an urban district of Korea

Jeonghun Song et al.

ENERGY (2019)

Add to Collection

Article Computer Science, Artificial Intelligence

Portfolio formation with preselection using deep learning from long-term financial data

Wuyu Wang et al.

EXPERT SYSTEMS WITH APPLICATIONS (2019)

Add to Collection

Article Economics

Diversifying portfolios of US stocks with crude oil and natural gas: A regime-dependent optimization with several risk measures

Hayette Gatfaoui

ENERGY ECONOMICS (2019)

Add to Collection

Review Computer Science, Information Systems

Systematic analysis and review of stock market prediction techniques

Dattatray P. Gandhmal et al.

COMPUTER SCIENCE REVIEW (2019)

Add to Collection

Article Economics

Forecasting the aggregate oil price volatility in a data-rich environment

Feng Ma et al.

ECONOMIC MODELLING (2018)

Add to Collection

Article Economics

Robust portfolio optimization for electricity planning: An application based on the Brazilian, electricity mix

Oswaldo L. V. Costa et al.

ENERGY ECONOMICS (2017)

Add to Collection

Article Economics

Portfolio optimization of renewable energy assets: Hydro, wind, and photovoltaic energy in the regulated market in Brazil

Daywes Pinheiro Neto et al.

ENERGY ECONOMICS (2017)

Add to Collection

Article Thermodynamics

Optimization of China's energy structure based on portfolio theory

Cuixia Gao et al.

ENERGY (2014)

Add to Collection

Article Management

Worst-case robust Omega ratio

Michalis Kapsos et al.

EUROPEAN JOURNAL OF OPERATIONAL RESEARCH (2014)

Add to Collection

Article Economics

Oil price shocks and stock market activities: Evidence from oil-importing and oil-exporting countries

Yudong Wang et al.

JOURNAL OF COMPARATIVE ECONOMICS (2013)

Add to Collection

Article Business, Finance

Applied Optimization in Global Efficient Portfolio Construction Using Earning Forecasts

Shijie Deng et al.

JOURNAL OF INVESTING (2013)

Add to Collection

Article Computer Science, Interdisciplinary Applications

Combined forecasts in portfolio optimization: A generalized approach

Ozden Ustun et al.

COMPUTERS & OPERATIONS RESEARCH (2012)

Add to Collection

Article Computer Science, Artificial Intelligence

An Adaptive Neuro-Fuzzy System for Stock Portfolio Analysis

Meysam Alizadeh et al.

INTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS (2011)

Add to Collection

Article Thermodynamics

Optimization of China's generating portfolio and policy implications based on portfolio theory

Lei Zhu et al.

ENERGY (2010)

Add to Collection

Article Economics

The performance of composite forecast models of value-at-risk in the energy market

Yen-Chen Chiu et al.

ENERGY ECONOMICS (2010)

Add to Collection

Article Thermodynamics

Mean-risk efficient portfolio analysis of demand response and supply resources

Shi-Jie Deng et al.

ENERGY (2009)

Add to Collection

Article Computer Science, Artificial Intelligence

Prediction-based portfolio optimization model using neural networks

Fabio D. Freitas et al.

NEUROCOMPUTING (2009)

Add to Collection

Article Computer Science, Theory & Methods

Fuzzy portfolio optimization under downside risk measures

Enriqueta Vercher et al.

FUZZY SETS AND SYSTEMS (2007)

Add to Collection

Article Business, Finance

Conditional value-at-risk for general loss distributions

RT Rockafellar et al.

JOURNAL OF BANKING & FINANCE (2002)

Add to Collection

© Peeref 2019-2024. All rights reserved.