Yaohao Peng

Universidade de Brasília - UnB, Management Department, Department Member

Followers

Following

Co-authors

Public Views

Graduated in International Relations at University of Brasília (2014). Master in Finance and Quantitative Methods at University of Brasília (2016). Ph. D. in Finance and Quantitative Methods at University of Brasília (2019). Has teaching experience in undergraduate courses (Department of Business Administration/University of Brasilia, 2016 - ). He was the Special Advisor on Data Science at the Brazilian Ministry of Economy (SPE/ME, 2019 - 2020), and he is currently Coordinator General for Agri-environmental Business to the Secretariat of Economic Policy at the Brazilian Ministry of Economy (SPE/ME, 2020 - ). Topics of interest include finance, nonlinear models, artificial intelligence, financial econometrics, machine learning, econophysics, game theory, and international political economy.
Supervisors: Pedro Henrique Melo Albuquerque

less

Muqtedar Khan

University of Delaware

Steven Pinker

Harvard University

Don Ross

University College Cork

Colin Williams

The University of Sheffield

Armando Marques-Guedes

UNL - New University of Lisbon

Noe Cornago

University of the Basque Country, Euskal Herriko Unibertsitatea

Nebojsa Davcik, Ph.D.

EM NORMANDIE

Iolanda Craifaleanu

Technical University Of Civil Engineering, Bucharest

Filippo Zatti

Università degli Studi di Firenze (University of Florence)

Pablo Rivas Perea

Baylor University

InterestsView All (17)

Uploads

Papers by Yaohao Peng

Machine learning methods for financial forecasting and trading profitability: Evidence during the Russia–Ukraine war

REGE Revista de Gestão, May 21, 2024

Purpose-This study aims to evaluate the effectiveness of machine learning models to yield profita... more 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 periodsin terms of generating abnormal gains over the marketwas 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.

Yaohao Peng

Uploads

Papers by Yaohao Peng

Log In