A Bayesian Network Model to Improve Stock Market Trend Following Strategies

  • Fabio Katsumi USP
  • Edson S. Gomi USP

Resumo


Traditional trend-following models have been used for many years to invest in various asset classes. In this paper we propose a Bayesian Network architecture to enhance classical trend following performance applied to the US stock index. The results show that a Bayesian Network that considers other market variables outperforms both traditional trend following and buy and hold strategies.
Palavras-chave: Bayesian Network, Stock Market, Trend Following Strategy

Referências

Bland, G. (2020). yfinance library – a complete guide. http://algotrading101.com/learn/yfinance-guide/. Last accessed on Feb 20, 2022.

Brownlee, J. (2019). How to backtest machine learning models for time series forecasting. [link]. Last accessed on Feb 15, 2022.

Chen, J. (2021). Index. https://www.investopedia.com/terms/i/index.asp. Last accessed on Apr 07, 2022.

CME Group (2016). Report: The big picture: A cost comparison of futures and etfs. [link]. Last accessed on May 12, 2022.

Fazelabdolabadi, B. (2019). A hybrid bayesian-network proposition for forecasting the crude oil price. Financial Innovation, 5(1):30.

Fu, Z. and Wu, Q. (2017). Quantitative trading strategy of market states prediction based on hmm. In Proceedings of the 2017 2nd International Conference on Materials Science, Machinery and Energy Engineering (MSMEE 2017), pages 1309–1319. Atlantis Press.

Heckerman, D. (2008). A tutorial on learning with bayesian networks. In Holmes D.E., Jain L.C. (eds) Innovations in Bayesian Networks, volume 156, page 33–82. Springer, Berlin, Heidelberg.

Hull, J. (2015). Options, futures, and other derivatives. pages 24–48. Boston :Prentice Hall, 9th edition.

Hurst, B., Ooi, Y. H., and Pedersen, L. H. (2017). A century of evidence on trendfollowing investing. The Journal of Portfolio Management, 44(1):15–29.

Jensen, F. V. and Nielsen, T. D. (2007). Bayesian Networks and Decision Graphs. Springer Publishing Company, Incorporated, 2nd edition.

Kuepper, J. (2021). Cboe volatility index (vix). https://www.investopedia.com/terms/v/vix.asp. Last accessed on Apr 07, 2022.

Lefèvre, E. (1923). Reminiscences of a stock operator. New York: George H. Doran Company.

Lemperiere, Y., Deremble, C., Seager, P., Potters, M., and Bouchaud, J.-P. (2014). Two centuries of trend following. In The Journal of Investment Strategies, volume 3. Scutari, M. (2010). Learning bayesian networks with the bnlearn r package. In Journal of Statistical Software, volume 35, page 1–22.

Wang, L., Wang, Z., Zhao, S., and Tan, S. (2015). Stock market trend prediction using dynamical bayesian factor graph. In Expert Systems with Applications, volume 42. Yahoo (2022). yahoo!finance. https://finance.yahoo.com/. Last accessed on Feb 15, 2022.

Zhang, J., Cui, S., Xu, Y., Li, Q., and Li, T. (2018a). A novel data-driven stock price trend prediction system. In Expert Systems with Applications, volume 97, pages 60–69.

Zhang, M., Jiang, X., Fang, Z., Zeng, Y., and Xu, K. (2018b). High-order hidden markov model for trend prediction in financial time series. In Physica A: Statistical Mechanics and its Applications, volume 517.

Zhang, X.-d., Li, A., and Pan, R. (2016). Stock trend prediction based on a new status box method and adaboost probabilistic support vector machine. In Applied Soft Computing, volume 49.
Publicado
31/07/2022
KATSUMI, Fabio; GOMI, Edson S.. A Bayesian Network Model to Improve Stock Market Trend Following Strategies. In: BRAZILIAN WORKSHOP ON ARTIFICIAL INTELLIGENCE IN FINANCE (BWAIF), 1. , 2022, Niterói. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2022 . p. 81-92. DOI: https://doi.org/10.5753/bwaif.2022.223291.