Welcome to Francis Academic Press

Academic Journal of Computing & Information Science, 2022, 5(10); doi: 10.25236/AJCIS.2022.051004.

An Improved ARIMA Method Based on Functional Principal Component Analysis and Bidirectional Bootstrap and Its Application to Stock Price Forecasting


Chuyu Feng1, Minsong Gao2

Corresponding Author:
Chuyu Feng

1School of International Business Administration, South China Normal University, Guangzhou, Guangdong, 510000, China

2Department of Mathematical Sciences, Anhui University, Hefei, 230601, China


This paper proposes an improved ARIMA method based on functional principal component analysis and bi-directional bootstrap. The proposed method does not require a smoothness assumption, uses intraday prices as auxiliary information and considers their functional characteristics, and effectively performs a bias-variance trade-off in the forecasting model by using a bi-directional bootstrap method. This is achieved by forming a paired sample of ARIMA forecast residuals and functional characteristics, and then fitting the forecast residuals to the regression model using the two-way bootstrap method, thereby improving the forecast accuracy.In addition, the choice of regression model is free. The empirical results show that the proposed method has better predictive performance and is more robust than the ARIMA model. Finally, the proposed method can be extended to environmental science, social science and other fields to help deal with various prediction problems.


Stock Price Forecast, ARIMA, Functional Principal Component Analysis, Two-way Bootstrap

Cite This Paper

Chuyu Feng, Minsong Gao. An Improved ARIMA Method Based on Functional Principal Component Analysis and Bidirectional Bootstrap and Its Application to Stock Price Forecasting. Academic Journal of Computing & Information Science (2022), Vol. 5, Issue 10: 21-27. https://doi.org/10.25236/AJCIS.2022.051004.


[1] Chen D J, Du F X & Xia H. (2022). Stock forecasting based on combination of ARIMA and SVR rolling residual models. Computer Times (05), 76-81. doi:10.16644/j.cnki.cn33-1094/ TP.2022.05.019.

[2] Lin Zhengyang, Ni Xiaojie & Wang Bo. (2022). Short-term Prediction of Photovoltaic Building Integration Stock Based on improved ARIMA Model. Computer Times (07), 40-43. doi:10. 16644/j.cnki.cn33-1094/tp. 2022.07.010.

[3] An xiaodan & Li Xiaoxia. (2022). GDP Forecasting analysis of Yuncheng City based on ARIMA Model. Journal of Yuncheng University (03), 69-73+90. doi:10.15967/ j.cnki.cn 14-1316/ g4. 2022.03.018.

[4] Zha, H. & Shi, D. (2022). GDP Prediction of Jiangsu Province based on ARIMA Model. Journal of Lanzhou University of Arts and Sciences (Natural Science edition) (03),33-36+54. doi:10.13804/j.cnki. 2095-6991.2022.03.010.

[5] Zhao Yabo. (2019).Research on Quantitative Investment Based on Data Analysis (Master's thesis, Hebei University of  Technology). https://kns.cnki.net/KCMS/detail/ detail.aspx?dbname= CMFD 202201&filename=1021873458.nh

[6] Song Yuping & Sun Yankun. (2021). High frequency Financial time Series Prediction: An improved ARIMA model based on adaptive filtering method. Journal of Jilin University of Business and Technology (02), 82-86. doi:10.19520/j.cnki.issn1674-3288.2021.02.012.

[7] Sun Lili, Fang Hongbin, Zhu Xingxing, Hu Leiming & Qi Longwu. (2021). Journal of Fuyang Normal University (Natural Science edition) (02),97-101. doi:10.14096/j.cnki.cn 34-1069/n/ 2096-9341(2021)02-0097-05.