A Multimodal Ensemble Model for Predicting the Daily Close Price of Banking Stocks
Keywords:
Ensemble Learning, Random Forest Regressor, Multimodal Data, Sentiment Analysis, Stock Price PredictionAbstract
We introduce a multi-model lifting model for predicting the daily closing prices of major Indonesian banking stocks (BBCA, BBRI, BBNI, BMRI) that integrates quantitative market indicators and qualitative news sentiment features. The two primary data sources are daily historical stock prices (Open, High, Low, Close, and Volume) collected from Yahoo Finance and 61,173 financial news articles downloaded from popular web portals, published between 2022 and 2025. Sentiment extraction classified positive, neutral, and negative news for each headline, and content was made through the IndoBERT model, which aggregated the classification on a daily basis. Market features were augmented by a volatility measure based on daily high and low prices. The combined dataset was modeled by a Random Forest Regressor in 80:20 train-test ratio. This model had good predictive capabilities (R²>0.89 for all stocks and a maximum of 0.9564 for BMRI). The MAPE values were always below 2.2% and it could decrease to even 1.43%, as in the case of BBCA. These findings further indicate that the fusion of market signal and news sentiment does improve the prediction of price from a psychological perspective, where both long-term trend and short-term sentiment are captured
References
[1] R. Aljifri, ‘Investor psychology in the stock market: An empirical study of the impact of overconfidence on firm valuation’, Borsa Istanbul Review, vol. 23, no. 1, 2023, doi: 10.1016/j.bir.2022.09.010.
[2] M. Nabipour, P. Nayyeri, H. Jabani, S. Shahab, and A. Mosavi, ‘Predicting Stock Market Trends Using Machine Learning and Deep Learning Algorithms Via Continuous and Binary Data; A Comparative Analysis’, IEEE Access, vol. 8, 2020, doi: 10.1109/ACCESS.2020.3015966.
[3] E. Chong, C. Han, and F. C. Park, ‘Deep learning networks for stock market analysis and prediction: Methodology, data representations, and case studies’, Expert Syst Appl, vol. 83, 2017, doi: 10.1016/j.eswa.2017.04.030.
[4] H. P. Khandagale, R. Patil, S. Patil, and D. Bhosale, ‘Predicting Stock Prices with Machine Learning using Comparative Analysis of Random Forest Algorithm’, International Journal of Engineering Applied Sciences and Technology, vol. 8, no. 6, 2023, doi: 10.33564/ijeast.2023.v08i06.008.
[5] M. Nabipour, P. Nayyeri, H. Jabani, A. Mosavi, E. Salwana, and S. Shahab, ‘Deep learning for stock market prediction’, Entropy, vol. 22, no. 8, 2020, doi: 10.3390/E22080840.
[6] A. E. Khedr, S. E. Salama, and N. Yaseen, ‘Predicting stock market behavior using data mining technique and news sentiment analysis’, International Journal of Intelligent Systems and Applications, vol. 9, no. 7, 2017, doi: 10.5815/ijisa.2017.07.03.
[7] M. K. Daradkeh, ‘A Hybrid Data Analytics Framework with Sentiment Convergence and Multi-Feature Fusion for Stock Trend Prediction’, Electronics (Switzerland), vol. 11, no. 2, 2022, doi: 10.3390/electronics11020250.
[8] E. Naresh, B. J. Ananda, K. S. Keerthi, and M. R. Tejonidhi, ‘Predicting the Stock Price Using Natural Language Processing and Random Forest Regressor’, in IEEE International Conference on Data Science and Information System, ICDSIS 2022, 2022. doi: 10.1109/ICDSIS55133.2022.9915940.
[9] S. Gite, H. Khatavkar, K. Kotecha, S. Srivastava, P. Maheshwari, and N. Pandey, ‘Explainable stock prices prediction from financial news articles using sentiment analysis’, PeerJ Comput Sci, vol. 7, 2021, doi: 10.7717/PEERJ-CS.340.
[10] F. Koto, A. Rahimi, J. H. Lau, and T. Baldwin, ‘IndoLEM and IndoBERT: A Benchmark Dataset and Pre-trained Language Model for Indonesian NLP’, in COLING 2020 - 28th International Conference on Computational Linguistics, Proceedings of the Conference, 2020. doi: 10.18653/v1/2020.coling-main.66.
[11] K. S. Rekha and M. K. Sabu, ‘A cooperative deep learning model for stock market prediction using deep autoencoder and sentiment analysis’, PeerJ Comput Sci, vol. 8, 2022, doi: 10.7717/PEERJ-CS.1158.
[12] S. Srivastava, M. Pant, and V. Gupta, ‘Analysis and prediction of Indian stock market: a machine-learning approach’, International Journal of System Assurance Engineering and Management, vol. 14, no. 4, 2023, doi: 10.1007/s13198-023-01934-z.
[13] W. L. Yan, ‘Stock index futures price prediction using feature selection and deep learning’, North American Journal of Economics and Finance, vol. 64, 2023, doi: 10.1016/j.najef.2022.101867.
[14] Y. A and Dr. K. D, ‘Building a Stock Price Prediction Model using Random Forest Regression and Sentimental Analysis’, Interantional Journal Of Scientific Research In Engineering And Management, vol. 07, no. 03, 2023, doi: 10.55041/ijsrem18258.
[15] B. Kriswantara and R. Sadikin, ‘Machine LearningUsed Car Price Prediction with Random Forest Regressor Model’, Journal of Information Systems, Informatics and Computing Issue Period, vol. 6, no. 1, 2022, doi: 10.52362/jisicom.v6i1.752.
[16] S. Usmani and J. A. Shamsi, ‘LSTM based stock prediction using weighted and categorized financial news’, PLoS One, vol. 18, no. 3 March, 2023, doi: 10.1371/journal.pone.0282234.
[17] Q. Liu, Z. Tao, Y. Tse, and C. Wang, ‘Stock market prediction with deep learning: The case of China’, Financ Res Lett, vol. 46, 2022, doi: 10.1016/j.frl.2021.102209.
[18] Y. Gao, R. Wang, and E. Zhou, ‘Stock Prediction Based on Optimized LSTM and GRU Models’, Sci Program, vol. 2021, 2021, doi: 10.1155/2021/4055281.
[19] W. Jiang, ‘Applications of deep learning in stock market prediction: Recent progress’, 2021. doi: 10.1016/j.eswa.2021.115537.
[20] A. L. Awad, S. M. Elkaffas, and M. W. Fakhr, ‘Stock Market Prediction Using Deep Reinforcement Learning’, Applied System Innovation, vol. 6, no. 6, 2023, doi: 10.3390/asi6060106.
[21] C. Schröer, F. Kruse, and J. M. Gómez, ‘A systematic literature review on applying CRISP-DM process model’, in Procedia Computer Science, 2021. doi: 10.1016/j.procs.2021.01.199.
[22] D. Chicco, M. J. Warrens, and G. Jurman, ‘The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation’, PeerJ Comput Sci, vol. 7, 2021, doi: 10.7717/PEERJ-CS.623.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Ego Widiarto, Dini Amalia, Muhammad Ilham Choiruddin (Author)
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
