Thống kê Bayes và ứng dụng trong dự báo giá chứng khoán của các ngân hàng và công ty tài chính ở Việt Nam

Đạt Nguyễn Phát; Hoa Lê Thanh; Bảo Phạm Thế

doi:10.24311/jabes/2020.31.04.2

Authors

Đạt Nguyễn Phát Trường Đại học Kinh tế TP. Hồ Chí Minh Author
Hoa Lê Thanh Trường Đại học Kinh tế - Luật, Đại học Quốc gia TP. Hồ Chí Minh Author
Bảo Phạm Thế Trường Đại học Sài Gòn Author

DOI:

https://doi.org/10.24311/jabes/2020.31.04.2

Keywords:

Bayesian statistics, Stock price forecasts, Bank securities code, Financial companies

Abstract

Forecasting has gained much attention in recent years, especially in economics and finance sectors. Once the forecast is good enough, the result will be helpful for enterprises in making decisions as well as for investors in maximizing profit. According to Decision No. 242/QĐ-TTg dated February 28th, 2019 of the Vietnamese Prime Miniter approves the project "Restructuring the securities market and insurance market to 2020 and orientation to 2025", it requires companies to standardize their business operations, report accurately and transparently according to international standards. Thanks to transparent and accurate information, investors have sufficient information for making the most significant capital investment decisions. The Bayesian statistics combine past information and prior knowledge for making accurate forecasts. Short-term forecasting problems usually use the information at time ???? to predict the one at ???? + 1. However, for the Vietnamese stock market, investors need a prediction at ???? + 3, when it is possible for trading recently purchased stocks. Under these circumstances, investors could minimize potential risks.

References

Ariyo, A. A., Adewumi, A. O., & Ayo, C. K. (2014). Stock price prediction using the ARIMA model. UKSim-AMSS 16th International Conference on Computer Modelling and Simulation (pp. 106–112). doi: 10.1109/UKSim.2014.67

Bolstad, W. M., & Curran, J. M. (2016). Introduction to Bayesian Statistics. Hoboken, NJ, USA: John Wiley & Sons.

Gelman, A., Carlin, J. B., Stern, H. S., Dunson, D. B., Vehtari, A., & Rubin, D. B. (2013). Bayesian Data Analysis. New York: Chapman & Hall/CRC.

Guha, B., & Bandyopadhyay, G. (2016). Gold price forecasting using ARIMA model. Journal of Advanced Management Science, 4(2), 117–121.

Lê Thanh Hoa, Phạm Hoàng Uyên., & Nguyễn Đình Thiên. (2017a). Một phương pháp mới tìm khoảng mật độ hậu nghiệm cao nhất và ứng dụng. Tạp chí Phát triển Kinh tế, 28(10), 79–120.

Lê Thanh Hoa, Phạm Hoàng Uyên, & Nguyễn Phúc Sơn. (2017b). Sử dụng thống kê Bayes mờ trong dự báo tỷ giá và một số chỉ số kinh tế. Tạp chí Công nghệ Ngân hàng, 140, 92–100.

Le, H., Pham, U., Nguyen, P., & Pham, T. B. (2020). Improvement on Monte Carlo estimation of HPD intervals. Communications in Statistics - Simulation and Computation, 49(8), 2164–2180. doi: 10.1080/03610918.2018.1513141

Pham, U., Le, H. T., & Nguyen, T. (2017). Choosing the best model in fuzzy Bayesian statistics and its application in financial analysis. Science & Technology Development Journal - Economics - Law and Management, 1(Q2), 144–155.

Robert, C. (2007). The Bayesian Choice: From Decision-Theoretic Foundations to Computational Implementation. Springer Science & Business Media.

Tran, H. D., Nguyen, S., Le, H. T., & Pham, U. (2017). An alternative to p-values in Hypothesis testing with applications in model selection of stock price data. In V. Kreinovich, S. Sriboonchitta, & V.-N. Huynh (Eds.), Robustness in Econometrics (pp. 305–319). Springer.