Forecasting financial asset movements using ensemble learning for the implementation of a uncorrelated portfolio

• Gabriel Costa Baptista UEFS
• Carlos Alberto Rodrigues UEFS

DOI: https://doi.org/10.5753/erbase.2024.4399

Abstract

This article explores the application of ensemble learning techniques, including bagging, boosting, stacking, and voting, in trading algorithms designed for a portfolio of uncorrelated assets in the brazilian futures market. Based on Modern Portfolio Theory (MPT) principles, the research aims to mitigate risks and improve prediction accuracy by applying the walk-forward method to adjust the models to the data continuously. The effectiveness of the predictions is evaluated using traditional metrics, while the performance of the trading strategies is analyzed by considering the integration of the forecasts.

References

Asad, M. (2015). Optimized stock market prediction using ensemble learning. In 9th International Conference on Application of Information and Communication Technologies (AICT), Rostov on Don, Russia.

Barber, B. and Odean, T. (2000). Trading is hazardous to your wealth: the common stock investment performance of individual investors. SSRN. [link].

Cavalcante, R. C., Brasileiro, R. C., Souza, V. L. F., Nobrega, J. P., and Oliveira, A. L. I. (2016). Computational intelligence and financial markets: A survey and future directions. Expert Systems with Applications, 55:194–211.

Chekhlov, A., Uryasev, S., and Zabarankin, M. (2005). Drawdown measure in portfolio optimization. International Journal of Theoretical and Applied Finance, 8(1):13–58.

Golosnoy, V., Gribisch, B., and Seifert, M. (2022). Sample and realized minimum variance portfolios: Estimation, statistical inference, and tests. Wiley Interdisciplinary Reviews: Computational Statistics, 14(5):1–18.

Hastie, T., Tibshirani, R., and Friedman, J. (2009). The elements of statistical learning: data mining, inference, and prediction. Springer.

Haykin, S. S. (1999). Neural networks: a comprehensive foundation. Pearson, 2nd edition.

Kumar, R. (2019). Machine learning quick reference: Quick and essential machine learning hacks for training smart data models. Packt Publishing.

Kyriakides, G. and Margaritis, K. (2019). Hands-On Ensemble Learning with Python: Build highly optimized ensemble machine learning models using scikit-learn and Keras. Packt Publishing.

Liu, Y. (2019). Python Machine Learning By Example. Packt Publishing.

Markowitz, H. (1952). Portfolio selection. The Journal of Finance, 7(1):77–91.

Nti, I., Adekoya, A., and Weyori, B. (2020). A comprehensive evaluation of ensemble learning for stock-market prediction. Journal of Big Data, 7(20):1–40.

Pinsky, E. (2018). Mathematical foundation for ensemble machine learning and ensemble portfolio analysis. SSRN, pages 1–48.

Santos, A. A. P. and Tessari, C. (2012). Técnicas quantitativas de otimização de carteiras aplicadas ao mercado de ações brasileiro. Revista Brasileira de Finanças, 10(3):369–363.

Sarkar, D. and Natarajan, V. (2019). Ensemble Machine Learning Cookbook: Over 35 practical recipes to explore ensemble machine learning techniques using Python. Packt Publishing.

Shen, W., Wang, B., Pu, J., and Wang, J. (2019). The kelly growth optimal portfolio with ensemble learning. In The Thirty-Third AAAI Conference on Artificial Intelligence, pages 1134–1141.