การพยากรณ์ราคาหุ้นโดยใช้การวิเคราะห์อนุกรมเวลา SARIMA

Salman  Saleng; Muhaimin  Chena; Somsri  Jarupadung; Wararat  Jakawat; Sirirut Vanichayobon

Authors

Salman Saleng Computer Science, Division of Computational Science, Faculty of Science, Prince of Songkla University
Muhaimin Chena Computer Science, Division of Computational Science, Faculty of Science, Prince of Songkla University
Somsri Jarupadung Computer Science, Division of Computational Science, Faculty of Science, Prince of Songkla University
Wararat Jakawat Computer Science, Division of Computational Science, Faculty of Science, Prince of Songkla University
Sirirut Vanichayobon Computer Science, Division of Computational Science, Faculty of Science, Prince of Songkla University

Keywords:

Time series, SARIMA, Stock forecasting, RMSE

Abstract

This article presents stock price forecasting using SARIMA time series analysis, which is suitable for seasonal data. The study utilizes daily closing prices of CP All Public Company Limited (CPALL) stock from 2014 to 2024. The analysis process includes data collection, data formatting and cleaning, exploratory data analysis, and the creation and testing of the SARIMA model using Python on Google Colab. The research findings indicate that the SARIMA(0,1,1)(0,0,2,12) model can effectively forecast stock price trends with an RMSE of 6.226 baht, which represents a low average deviation between forecasted and actual prices. This reflects the accuracy of the model in capturing stock price trends. These research findings can effectively support long-term investment decision-making.

References

Artley, B. (2022, April 26). Time series forecasting with ARIMA, SARIMA and SARIMAX. Towards Data Science. https://towardsdatascience.com/time-series-forecasting-with-arima-sarima-and-sarimax-ee61099e78f6

Box, G. E. P., Jenkins, G. M., Reinsel, G. C., & Ljung, G. M. (2015). Time series analysis: Forecasting and control (5th ed.). John Wiley & Sons.

Dickey, D. A., & Fuller, W. A. (1979). Distribution of the estimators for autoregressive time series with a unit root. Journal of the American Statistical Association, 74(366a), 427–431.

Google Colab. (2024). Google Colaboratory. https://colab.research.google.com

Handayani, N. R. W. T., Maslim, M., & Mudjihartono, P. (2020). Forecasting of catfish sales by time series using the SARIMA method. Jurnal Buana Informatika, 11(2), 84–93.

Microsoft Power BI. (2024). Microsoft Power BI. https://powerbi.microsoft.com

Saadeddin, Z. (2024). ARIMA for time series forecasting: Complete guide. DataCamp. https://www.datacamp.com/tutorial/arima

Selvakumar, S., Renugadevi, G., Vinishah, N., & Yashwanth, R. (2024). Sales forecasting based on time series analysis. In Proceedings of the 2024 International Conference on Science and Technology Engineering and Management (ICSTEM 2024) (pp. 658–664).

Sirisha, U. M., Belavagi, M. C., & Attigeri, G. (2022). Profit prediction using ARIMA, SARIMA and LSTM models in time series forecasting: A comparison. IEEE Access, 10, 124715–124727.

Subhash. (2023, February 27). Augmented Dickey-Fuller test in time-series analysis. AskPython. https://www.askpython.com/python/examples/augmented-dickey-fuller-test-time-series

Szostek, K., Mazur, D., Drałus, G., & Kusznier, J. (2024). Analysis of the effectiveness of ARIMA, SARIMA, and SVR models in time series forecasting: A case study of wind farm energy production. Energies, 17(19), 4803. https://doi.org/10.3390/en17194803

Tibshirani, R. (2023). Lecture 1: Characteristics and examples of time series data. https://www.stat.berkeley.edu/~ryantibs/timeseries-f23/lectures/characteristics.pdf