Research on Stock Index Prediction Based on SARIMA-BP-KPCA+RF Model

Fengying Yan

doi:10.62051/1t4vhs76

Authors

Fengying Yan

DOI:

https://doi.org/10.62051/1t4vhs76

Keywords:

Stock price prediction; SARIMA; BP neural network; KPCA+RF.

Abstract

The prediction of stock prices plays a vital role in guiding investors' decision - making processes and managing risks within the financial market. The stock price of ADANIPORTS is influenced by multidimensional data and exhibits nonlinear dynamic characteristics. This study is based on Yahoo Finance data, calculating 8 technical indicators including KDJ and RSI. After feature screening, seasonal autoregressive integral moving average model (SARIMA), backpropagation neural network model (BP neural network), and kernel principal component analysis random forest model (KPCA+RF) are constructed and their performance is compared. The experiment showed that the MAE of SARIMA was 8.4983 and the R² was 0.9668; The MAE of the BP neural network is 13.7540 and the R² is 0.9797; The MAE of KPCA+RF is 10.3501 and the R² is 0.9832, indicating the best prediction accuracy. The study has verified the effectiveness of ensemble learning and nonlinear dimensionality reduction, providing a multi model comparative analysis framework for stock prediction and having methodological reference value.

Downloads

Download data is not yet available.

References

[1] Wang R. Research on stock price prediction based on similarity measurement and dual-channel multi-scale hybrid neural network. Shandong University of Technology, 2024.

[2] Guan M. Pre-investment enterprise financial crisis identification scheme based on KPCA-XGBoost. Shanghai Normal University, 2021.

[3] Zhang Y, Li L. RF-MIP-LSTM stock price prediction model. Comput Eng Appl, 2024, 60(17): 272 – 281.

[4] Fu W. Research on stock price prediction based on ARIMA-RF combination model. Sci Technol Innov, 2023, (08): 40 – 43.

[5] Yang B. SARIMA stock price index prediction modeling based on neural network. Entrepreneur World, 2010, (04): 109 – 110.

[6] Zhao H. Research on stock price prediction method based on ARIMA-BP neural network and sentiment analysis. Shenyang Industry University, 2021.

[7] Ma G. Research on stock index prediction based on ARIMA-LSTM-BP combination model. Kashgar University, 2024.

[8] Li J. Stock index futures price prediction and quantitative strategy construction based on KPCA-gcForest. Northwest University, 2021.

[9] Wu C, Xu F, Duan M, Zhang L. Comparative study on the prediction of tuberculosis incidence in China based on SARIMA model and LSTM neural network model. China Port Sci Technol, 2025, 7(03): 4 – 12.

[10] Ren D, Xing B, Tian Y, Liu W. A PM2.5 prediction model based on BP neural network. China Sci Technol Inf, 2025, (08): 70 – 72.

[11] Xu X, Pan T. Research on wind farm power prediction method based on KPCA-RF. Renew Energy, 2018, 36(09): 1323 – 1327.