Yaohao Peng
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Yaohao Peng has a total of 31 co-authors. Here are the top co-authors by number of shared publications:
Pedro Henrique Melo Albuquerque
University of Brasilia
3 shared publicationsCayan Atreio Portela Bárcena Saavedra
2 shared publications- Herbert Kimura
Department of Business Management, Faculty of Economics, Business Management, Accounting and Public Policy Management (FACE), University of Brasília, Brasília 70910-900, DF, Brazil
2 shared publications - Igor Ferreira Do Nascimento
Federal Institute of Piauí, Campus Teresina-Central, 64000-040 Teresina, Piauí, Brazil
2 shared publications João Gabriel de Moraes Souza
2 shared publications- João Gabriel de Moraes Souza
Universidade de Brasília
2 shared publications
Latest Publications
- 19 July 2024
- Published by Elsevier in International Review of Financial Analysis
- Vol. 95
Chaos, overfitting and equilibrium: To what extent can machine learning beat the financial market?
- 19 July 2024
- Published by Elsevier in International Review of Financial Analysis
- Vol. 95
Chaos, overfitting and equilibrium: To what extent can machine learning beat the financial market?
- Open Access
- 21 May 2024
- Published by Emerald Publishing in Revista de Gestão
- Vol. 31 (2) , 152-165
Machine learning methods for financial forecasting and trading profitability: Evidence during the Russia–Ukraine war
Purpose: This study aims to evaluate the effectiveness of machine learning models to yield profitability over the market benchmark, notably in periods of systemic instability, such as the ongoing war between Russia and Ukraine.Design/methodology/approach: This study made computational experiments using support vector machine (SVM) classifiers to predict stock price movements for three financial markets and construct profitable trading strategies to subsidize investors’ decision-making.Findings: On average, machine learning models outperformed the market benchmarks during the more volatile period of the Russia–Ukraine war, but not during the period before the conflict. Moreover, the hyperparameter combinations for which the profitability is superior were found to be highly sensitive to small variations during the model training process.Practical implications: Investors should proceed with caution when applying machine learning models for stock price forecasting and trading recommendations, as their superior performance for volatile periods – in terms of generating abnormal gains over the market – was not observed for a period of relative stability in the economy.Originality/value: This paper’s approach to search for financial strategies that succeed in outperforming the market provides empirical evidence about the effectiveness of state-of-the-art machine learning techniques before and after the conflict deflagration, which is of potential value for researchers in quantitative finance and market professionals who operate in the financial segment.
- 21 May 2024
- Published by Emerald Publishing in Revista de Gestão
- Vol. 31 (2) , 152-165
Open AccessMachine learning methods for financial forecasting and trading profitability: Evidence during the Russia–Ukraine war
Purpose: This study aims to evaluate the effectiveness of machine learning models to yield profitability over the market benchmark, notably in periods of systemic instability, such as the ongoing war between Russia and Ukraine.Design/methodology/approach: This study made computational experiments using support vector machine (SVM) classifiers to predict stock price movements for three financial markets and construct profitable trading strategies to subsidize investors’ decision-making.Findings: On average, machine learning models outperformed the market benchmarks during the more volatile period of the Russia–Ukraine war, but not during the period before the conflict. Moreover, the hyperparameter combinations for which the profitability is superior were found to be highly sensitive to small variations during the model training process.Practical implications: Investors should proceed with caution when applying machine learning models for stock price forecasting and trading recommendations, as their superior performance for volatile periods – in terms of generating abnormal gains over the market – was not observed for a period of relative stability in the economy.Originality/value: This paper’s approach to search for financial strategies that succeed in outperforming the market provides empirical evidence about the effectiveness of state-of-the-art machine learning techniques before and after the conflict deflagration, which is of potential value for researchers in quantitative finance and market professionals who operate in the financial segment.
- Open Access
- 1 March 2024
- Published by Qeios Ltd
Review of: "The Russian-Ukrainian War as an Impetus to the Destabilization of World Business: Reactions of Stock Markets"
The paper addresses relevant topics, and its main results can provide useful insights for the evaluation of global financial dynamics in light of events with structural implications. Some recommendations for improvement are listed below: * The abst...
- 1 March 2024
- Published by Qeios Ltd
Open AccessReview of: "The Russian-Ukrainian War as an Impetus to the Destabilization of World Business: Reactions of Stock Markets"
The paper addresses relevant topics, and its main results can provide useful insights for the evaluation of global financial dynamics in light of events with structural implications. Some recommendations for improvement are listed below: * The abst...
- 6 November 2023
- Published by Springer Nature in Computational Economics
- Vol. 64 (3) , 1857-1890
A Machine Learning-Based Analysis on the Causality of Financial Stress in Banking Institutions
- 6 November 2023
- Published by Springer Nature in Computational Economics
- Vol. 64 (3) , 1857-1890
A Machine Learning-Based Analysis on the Causality of Financial Stress in Banking Institutions
- 24 July 2022
- Published by Wiley in Journal of Forecasting
- Vol. 41 (8) , 1701-1724
Making the whole greater than the sum of its parts: A literature review of ensemble methods for financial time series forecasting
This paper discusses the application of ensemble techniques for the prediction of time series, presenting an in‐depth review of the main techniques and algorithms used by the recent literature, with emphasis on the bootstrap aggregation (bagging) and boosting approaches. We also discuss the theoretical foundations of the ensemble‐based models, presenting measures of model stability and the main aggregation methods to combine the forecasts of the individual models, as well as recommendations for future developments for related research agendas.
- 24 July 2022
- Published by Wiley in Journal of Forecasting
- Vol. 41 (8) , 1701-1724
Making the whole greater than the sum of its parts: A literature review of ensemble methods for financial time series forecasting
This paper discusses the application of ensemble techniques for the prediction of time series, presenting an in‐depth review of the main techniques and algorithms used by the recent literature, with emphasis on the bootstrap aggregation (bagging) and boosting approaches. We also discuss the theoretical foundations of the ensemble‐based models, presenting measures of model stability and the main aggregation methods to combine the forecasts of the individual models, as well as recommendations for future developments for related research agendas.
- 2 November 2021
- Published by Springer Nature
- p. 673-730
Understanding COVID-19 in Brazil: Socioeconomic Impacts, Statistical Analysis and Future Challenges
- 2 November 2021
- Published by Springer Nature
- p. 673-730
Understanding COVID-19 in Brazil: Socioeconomic Impacts, Statistical Analysis and Future Challenges
- Open Access
- 1 September 2021
- Published by Elsevier in Machine Learning with Applications
- Vol. 5
Machine learning algorithms for fraud prediction in property insurance: Empirical evidence using real-world microdata
- 1 September 2021
- Published by Elsevier in Machine Learning with Applications
- Vol. 5
Open AccessMachine learning algorithms for fraud prediction in property insurance: Empirical evidence using real-world microdata
- Open Access
- 1 September 2021
- Published by Elsevier in Machine Learning with Applications
- Vol. 5
Feature selection and deep neural networks for stock price direction forecasting using technical analysis indicators
- 1 September 2021
- Published by Elsevier in Machine Learning with Applications
- Vol. 5
Open AccessFeature selection and deep neural networks for stock price direction forecasting using technical analysis indicators
- Open Access
- 21 December 2020
- Published by Linhas Críticas in Revista Gestão & Saúde
- Vol. 11 (3) , 261-280
análise estatística comparativa das evidências de subnotificação da COVID-19 no Brasil
Este artigo investigou a subnotificação da COVID-19 nos estados brasileiros tomando como base os dados da Coreia do Sul e da Itália como referências de testagem e avaliando a subnotificação relativa com base em suas respectivas taxas de letalidade. Desenvolveu-se modelo estatístico que incorpora aspectos temporais e espaciais, o qual analisou a dispersão da COVID-19 a partir de um epicentro para três unidades federativas brasileiras e quatro estados norte-americanos; a influência relativa da malha rodoviária para a dispersão da COVID-19 nesses estados também foi verificada. Os resultados indicam que 16 das 27 unidades federativas brasileiras apresentaram notificação superior aos níveis observados da Itália, embora todas tenham demostrado evidências de subnotificação quando comparadas com os níveis observados da Coreia do Sul. Evidências de subnotificação do interior em relação à capital de cada estado também foram discutidas. Os achados do estudo podem contribuir para a melhor compreensão das heterogeneidades de subnotificação para diferentes regiões do Brasil, bem como auxiliar no diagnóstico da demanda dos sistemas regionais de saúde e na estimativa da duração da pandemia em nível regional.
- 21 December 2020
- Published by Linhas Críticas in Revista Gestão & Saúde
- Vol. 11 (3) , 261-280
Open Accessanálise estatística comparativa das evidências de subnotificação da COVID-19 no Brasil
Este artigo investigou a subnotificação da COVID-19 nos estados brasileiros tomando como base os dados da Coreia do Sul e da Itália como referências de testagem e avaliando a subnotificação relativa com base em suas respectivas taxas de letalidade. Desenvolveu-se modelo estatístico que incorpora aspectos temporais e espaciais, o qual analisou a dispersão da COVID-19 a partir de um epicentro para três unidades federativas brasileiras e quatro estados norte-americanos; a influência relativa da malha rodoviária para a dispersão da COVID-19 nesses estados também foi verificada. Os resultados indicam que 16 das 27 unidades federativas brasileiras apresentaram notificação superior aos níveis observados da Itália, embora todas tenham demostrado evidências de subnotificação quando comparadas com os níveis observados da Coreia do Sul. Evidências de subnotificação do interior em relação à capital de cada estado também foram discutidas. Os achados do estudo podem contribuir para a melhor compreensão das heterogeneidades de subnotificação para diferentes regiões do Brasil, bem como auxiliar no diagnóstico da demanda dos sistemas regionais de saúde e na estimativa da duração da pandemia em nível regional.
- 1 October 2020
- Published by Elsevier in Chaos, Solitons & Fractals
- Vol. 139, 110055
An empirical overview of nonlinearity and overfitting in machine learning using COVID-19 data
- 1 October 2020
- Published by Elsevier in Chaos, Solitons & Fractals
- Vol. 139, 110055
An empirical overview of nonlinearity and overfitting in machine learning using COVID-19 data