A HYBRID DEEP LEARNING AND TREE BOOSTING APPROACH FOR BBCA STOCK PRICE FORECASTING WITH SHAP EXPLAINABILITY
Abstract
Forecasting stock price movement is a complex task due to nonlinear patterns, market volatility, and the influence of various technical and fundamental factors. This study proposes a hybrid forecasting framework that integrates the sequential learning capability of the Gated Recurrent Unit (GRU) with the nonlinear regression strength of Extreme Gradient Boosting (XGBoost) to predict the daily closing price of Bank Central Asia Tbk (BBCA). The dataset consists of historical BBCA prices from 2017 to 2025 and includes technical indicators such as moving averages, RSI, MACD, and Bollinger Bands. An 80:20 chronological split was used to evaluate model generalization through MAE, RMSE, MAPE, and R² metrics. Experimental results show that the hybrid GRU–XGBoost model outperforms both standalone GRU and XGBoost models, achieving the best performance with MAE of 229.09, RMSE of 312.26, and R² of 0.874 MAPE of 2.37%. Furthermore, SHAP-based explainability analysis highlights that price-based features and trend–momentum indicators contribute most significantly to the prediction output, while the GRU-derived sequential feature enhances temporal pattern recognition. These findings demonstrate that combining deep learning and boosting techniques produces a more accurate and interpretable forecasting model suitable for financial decision-making and risk analysis.
References
M. A. Rad, L. M. Lefsrud, M. T. Hendry, A. C. Cen, and S. Soltaninejad, “Analysis of freight train passing a stop signal using machine learning: Application of XGBoost and SHAP,” J. Rail Transp. Plan. Manag., vol. 35, no. April, p. 100532, 2025, doi: 10.1016/j.jrtpm.2025.100532.
B. Gülmez, “Stock price prediction with optimized deep LSTM network with artificial rabbits optimization algorithm,” Expert Syst. Appl., vol. 227, no. May, p. 120346, 2023, doi: 10.1016/j.eswa.2023.120346.
J. Che, “A Short-Term Hybrid Prediction Model for Offshore Wind Power Based on EEMD and LSTM,” 2023 6th Int. Conf. Energy, Electr. Power Eng., pp. 1225–1229, 2023, doi: 10.1109/CEEPE58418.2023.10167250.
Q. Liu, Y. Hu, and H. Liu, “Enhanced stock price prediction with optimized ensemble modeling using multi-source heterogeneous data: Integrating LSTM attention mechanism and multidimensional gray model,” J. Ind. Inf. Integr., vol. 42, no. November, p. 100711, 2024, doi: 10.1016/j.jii.2024.100711.
C. Ravikumar, J. Manoranjini, S. Pallavi, U. Naresh, S. Telang, and S. Kiran, “Advancing Malware Detection Using Memory Analysis and Explainable AI Approach,” 2nd Int. Conf. Intell. Cyber Phys. Syst. Internet Things, ICoICI 2024 - Proc., no. ICoICI, pp. 518–523, 2024, doi: 10.1109/ICoICI62503.2024.10696406.
S. Hossain and G. Kaur, “Stock Market Prediction: XGBoost and LSTM Comparative Analysis,” 2024 3rd Int. Conf. Artif. Intell. Internet Things, AIIoT 2024, no. AIIoT, pp. 1–6, 2024, doi: 10.1109/AIIoT58432.2024.10574794.
H. E. Yu, L. I. J. Ming, R. Sumei, and Z. Shuping, “A Hybrid Model for Financial Time Series Forecasting — Integration of EWT , ARIMA With The Improved ABC Optimized ELM,” pp. 84501–84518, 2020, doi: 10.1109/ACCESS.2020.2987547.
J. Timko, R. El Shawi, and S. Tomasiello, “Optimizing stock price forecasting: a hybrid approach using fuzziness and automated machine learning,” Expert Syst. Appl., vol. 295, no. December 2024, 2024, doi: 10.1016/j.eswa.2025.128844.
Z. Liu, Z. Su, L. Shang, H. Sun, and B. Zhao, “An approach to stock price prediction based on improved EEMD and attention-enhanced BiLSTM,” Expert Syst. Appl., vol. 284, p. 127802, 2025, doi: 10.1016/j.eswa.2025.127802.
H. Notaria, S. Shah, D. Thopte, H. Soneji, P. Bari, and K. Deulkar, “Comparative Analysis of Stock Price Prediction using Time Series Models,” 2024 8th Int. Conf. Comput. Commun. Control Autom. ICCUBEA 2024, pp. 1–6, 2024, doi: 10.1109/ICCUBEA61740.2024.10775112.
Z. Xiao, S. Li, and Z. Lin, “A Hybrid Modeling Approach for Forecasting the Volatility of REITs Index in US Market,” 2012 Int. Conf. Manag. Sci. Eng. 19th Annu. Conf. Proc., pp. 1861–1867, 2012, doi: 10.1109/ICMSE.2012.6414425.
M. R. Hossain, M. T. Ismail, and J. Hossain, “Stock Price Prediction Using Empirical Mode Decomposition Based Theta Method and Forecast Combination,” 2021 Int. Conf. Decis. Aid Sci. Appl., pp. 1115–1119, 2021, doi: 10.1109/DASA53625.2021.9682235.
L. Heistrene et al., “An Improved and Explainable Electricity Price Forecasting Model via SHAP-Based Error Compensation Approach,” IEEE Trans. Artif. Intell., vol. 6, no. 1, pp. 159–168, 2025, doi: 10.1109/TAI.2024.3455313.
T. D. Hastuti, R. Sanjaya, and F. Koeswoyo, “The Investment Opportunity, Information Technology and Financial Performance of SMEs,” Proc. - Int. Conf. Comput. Inf. Sci. Sustain. Tomorrow with Digit. Innov. ICCOINS 2021, no. July 2021, pp. 247–251, 2021, doi: 10.1109/ICCOINS49721.2021.9497182.
P. Thanathamathee, S. Sawangarreerak, and D. N. M. Nizam, “Enhancing Going Concern Prediction With Anchor Explainable AI and Attention-Weighted XGBoost,” IEEE Access, vol. 12, no. March, pp. 68345–68363, 2024, doi: 10.1109/ACCESS.2024.3401007.
M. Aravindhan and D. Manikavelan, “Decomposition-Based Transformer-LSTM Framework for Stock Index Forecasting,” 2025 3rd World Conf. Commun. & Comput., pp. 1–6, 2025, doi: 10.1109/WCONF64849.2025.11233358.
DOI: https://doi.org/10.33387/jiko.v9i1.11102
Refbacks
- There are currently no refbacks.