Welcome to Francis Academic Press
Login | Register

Academic Journal of Computing & Information Science, 2024, 7(11); doi: 10.25236/AJCIS.2024.071117.

A Novel Residual Correction Approach Based on a Hybrid GARCH and XGBoost Model

Author(s)

Jiahao Wang1, Jihong Zhang2, Yuxin Cai1

Corresponding Author:
Jiahao Wang
Affiliation(s)

1Department of Mathematics and Statistics, Northwest Normal University, Lanzhou, China

2Department of Information Technology, Lanzhou City University, Lanzhou, China

Abstract

The stock market’s inherent uncertainty and volatility make forecasting stock prices a highly challenging task in finance. Financial time series modeling plays a crucial role in addressing this issue. This study proposes a hybrid model combining ARIMA, GARCH, and XGBoost to improve the accuracy of stock opening price predictions. The hybrid approach adjusts ARIMA model residuals using GARCH and XGBoost, leveraging their complementary strengths. Historical opening price data from Hong Kong stocks were employed to train and validate the model. Comparative analyses with traditional single models and other hybrid models reveal that the proposed model demonstrates superior accuracy and robustness. These results highlight its potential to provide reliable decision-making support for investors in the stock market.

Keywords

Stock Price Forecasting, ARIMA-GARCH model, XGBoost model, Residual Correction

Cite This Paper

Jiahao Wang, Jihong Zhang, Yuxin Cai. A Novel Residual Correction Approach Based on a Hybrid GARCH and XGBoost Model. Academic Journal of Computing & Information Science (2024), Vol. 7, Issue 11: 127-134. https://doi.org/10.25236/AJCIS.2024.071117.

References

[1] Wu Y, Wen X, et al. Short-term stock price prediction based on ARIMA model[J]. Statistics and Decision Making, 2016, 23: 83-86. 

[2] Chen Y S, Tang Z J, Luo Y, et al. Research on stock price prediction by Pearson optimization combined with XGBoost algorithm[J]. Information Technology, 2018, 9: 84-89.

[3] Peng Y, Liu Y H, Zhang R F, et al. Modeling and analysis of stock price prediction based on LSTM[J]. Computer Engineering and Applications, 2019, 55: 209-212.

[4] Cao X, Zhao Z. Research on stock index forecasting based on ARIMA-GARCH and SVM mixed model [J]. Proceedings of 2022 International Conference on Software Data Processing and Information Technology, 2022, 1: 41-47.

[5] Feng C, Gao M. An Improved ARIMA Method Based on Functional Principal Component Analysis and Bidirectional Bootstrap and Its Application to Stock Price Forecasting[J]. Academic Journal of Computing Information Science, 2022, 5: 14-19.

[6] Jin B, Gao S, Tao Z, et al. ARIMA and Facebook Prophet Model in Google Stock Price Prediction[J]. Proceedings of Business and Economic Studies, 2022, 5: 60-66.

[7] Kahkashan K. Price Forecasting of Maruti Suzuki using ARIMA Model[J]. Parikalpana KIIT Journal of Management, 2022, 18: 90-98.

[8] Pratiwi L, Susetyo B, Sadik K, et al. Comparison of Transfer Function Model and ARIMA-GARCH on Daily Stock Data in Agribusiness and Trade Sector[J]. International Journal of Sciences: Basic and Applied Research, 2022, 61: 57-69.

[9] Ying X. Using ARIMA-GARCH Model to Analyze Fluctuation Law of International Oil Price[J]. Mathematical Problems in Engineering, 2022, 22: 11-17.

[10] Ayman A, Saleh B, and Faisal A. Stock price prediction using ARIMA versus XGBoost models: the case of the largest telecommunication company in the Middle East[J]. International Journal of Information Technology, 2023, 15: 1813-1818.

[11] Elangovan R, Gnanasekar F and Parayitam S. Day of the week effect in the Indian stock market[J]. International Journal of International Accounting and Finance, 2023, 11: 181-201.

[12] Goyal R, Adjemian K M, Glauber J, et al. Decomposing USDA Ending Stocks Forecast Errors[J]. Journal of Agricultural and Resource Economics, 2023, 48: 260-276.

[13] Hao Q J. The Application of the ARIMA-GARCH Hybrid Model for Forecasting the Apple Stock Price[J]. Journal of Intelligence and Knowledge Engineering, 2023, 1: 01-08.

[14] Jiancheng S, John G, Mohammad N, et al. Predicting Stock and Bond Market Returns with Emotions: Evidence from Futures Markets[J]. Journal of Behavioral Finance, 2023, 24: 333-344.

[15] Paravee M, Binxiong Z and Woraphon Y. Predicting Chinese stock prices using convertible bond: an evidence-based neural network approach[J]. Asian Journal of Economics and Banking, 2023, 7: 294-309.

[16] Yuan W K, Zhou Z T, et al. Research on the influencing factors of stock price volatility based on PCA-BP neural network[J]. Business and Exhibition Economics, 2023, 10: 99-101.