Comparative Analysis of Bayesian Approaches and Variant Methods in the Financial Field

Yilin Chen

doi:10.54097/38mmdr81

Authors

Yilin Chen

DOI:

https://doi.org/10.54097/38mmdr81

Keywords:

Component, Bayes’ theorem, Multinomial Naïve Bayes, Gaussian Naïve Bayes.

Abstract

It is important for researchers to select the most appropriate model for specific financial tasks. This comparative analysis describes the strengths, limitations, and trade-offs of Bayesian approaches and variant methods. Moreover, this study aims to compare Bayesian approaches and their variant methods in the financial field and assess their effectiveness and relevancy for stock price prediction. This study starts with a brief overview of Bayes’ Theorem, Naïve Bayes (NB), multinomial Naïve Bayes (NBM), and Gaussian Naïve Bayes (GNB). In the prediction of the Brazilian stock market, NBM demonstrates superior performance compared to other models in terms of accuracy, recall, and F1-score. In the meantime, the GNB and linear discriminant analysis-based combined model (GNB_LDA) exhibits superior performance in accuracy and F1-score, while the model incorporates GNB, standardization, and factor analysis (GNB_Z-Score_FA) excels in mean specificity in the prediction of seven different stocks. This study also suggests further exploration of hybrid models that combine the strengths of Bayesian models with other techniques to enhance financial analysis and decision-making.

Downloads

Download data is not yet available.

References

[1] T. Bayes, “LII. An essay towards solving a problem in the doctrine of chances. By the late Rev. Mr. Bayes, FRS communicated by Mr. Price, in a letter to John Canton, AMFR S,” Philosophical transactions of the Royal Society of London, vol. 53, pp. 370-418.

[2] P. S. Laplace, “Pierre-Simon Laplace philosophical essay on probabilities: translated from the fifth french edition of 1825 with notes by the translator,” Springer Science & Business Media, vol. 13, 1998.

[3] D. Ashby, “Bayesian statistics in medicine: a 25 year review,” Statistics in medicine, vol. 25, 2006, pp. 3589-3631.

[4] P. Myllymäki, “B-course: A web-based tool for Bayesian and causal data analysis,” International Journal on Artificial Intelligence Tools, vol. 11, 2002, pp. 369-387.

[5] B. G. Marcot, R. S. Holthausen, M. G. Raphael, “Using Bayesian belief networks to evaluate fish and wildlife population viability under land management alternatives from an environmental impact statement,” Forest ecology and management, vol. 153, 2001, pp. 29-42.

[6] S. Kuikka, V. Olli, “Uncertainties of climatic change impacts in Finnish watersheds: a Bayesian network analysis of expert knowledge,” Boreal Environment Research, vol. 2, 1997.

[7] L. Uusitalo, “Advantages and challenges of Bayesian networks in environmental modeling,” Ecological modeling, vol. 203, 2007, pp. 312-318.

[8] S. McCloskey, “Probabilistic reasoning and Bayesian networks,” Proc. Neural Netw. Mach. Learn. (ICSG), 2000.

[9] S. Xu, L. Yan, W. Zheng, “Bayesian multinomial Naïve Bayes classifier to text classification,” Advanced Multimedia and Ubiquitous Engineering: MUE/FutureTech, vol. 11, 2017.

[10] A. H. Jahromi, T. Mohammad, “A non-parametric mixture of Gaussian naive Bayes classifiers based on local independent features,” 2017 Artificial Intelligence and signal processing conference (AISP), 2017.

[11] Y. Reddy, P. Viswanath, B. E. Reddy, “Semi-supervised learning: A brief review,” Int. J. Eng. Technol, vol. 7, 2018, p. 81.

[12] U. Ozkaya, S. Levent, “Fine-tuning models comparisons on garbage classification for recyclability,” Unpublished.

[13] B. Neuenschwander, “Sentiment analysis for streams of web data: A case study of Brazilian financial markets,” Proceedings of the 20th Brazilian Symposium on Multimedia and the Web, 2014.

[14] E. K. Ampomah, G. Nyame, Z. Qin, “Stock market prediction with gaussian naïve bayes machine learning algorithm,” Informatica, vol. 45, 2021.