Acta Informatica Pragensia 2024, 13(1), 24-37 | DOI: 10.18267/j.aip.2263556
Optimized Ensemble Support Vector Regression Models for Predicting Stock Prices with Multiple Kernels
- Department of Computer Science and Technology, Sri Krishnadevaraya University, Anantapur, India
Stock forecasting is a complicated and daily challenge for investors because of the non-linearity of the market and the high volatility of financial assets such as stocks, bonds and other commodities. There is a need for a powerful and adaptive stock prediction model that handles complexities and provides accurate predictions. The support vector regression (SVR) model is one of the most prominent machine learning models for forecasting time series data. An ensemble hyperbolic tangent kernel SVR (HTK-SVR-BO) is proposed in this paper, combining Tanh and inverse Tanh kernels with Bayesian optimization. Combining the strengths of multiple kernels using the ensemble technique and then using optimization to identify the optimal values for each SVR model to enhance the ensemble model performance is possible. Our proposed model is compared with an ensemble SVR model (LPR-SVR-BO), which uses well-known SVR kernel types, including linear, polynomial and radial basis function (RBF). We apply the proposed models to Microsoft Corporation (MSFT) stock prices. The mean absolute error (MAE), mean squared error (MSE), root mean squared error (RMSE), R2 score (model accuracy) and mean absolute percentage error (MAPE) are the regression metrics used to compare the effectiveness of each ensemble model. In our comparison, HTK-SVR-BO performs better in terms of regression metrics compared to LPR-SVR-BO and achieves results of 0.27424, 0.13392, 0.36595, 0.99997 and 5.2331 respectively. According to the analysis, the proposed model is more predictive and may generalize to previously unknown data more effectively, so it can be accurate when forecasting future stock prices.
Keywords: Microsoft corporation (MSFT); Stock forecast; SVR; Hyperbolic tangent kernels (HTK); Linear polynomial RBF kernels (LPR); Ensemble model; Bayesian optimization (BO); Regression metrics
Received: September 12, 2023; Revised: December 5, 2023; Accepted: December 7, 2023; Prepublished online: January 13, 2024; Published: April 15, 2024 Show citation
References
- Alam, S., Sultana, N., & Hossain, S. M. Z. (2021). Bayesian optimization algorithm-based support vector regression analysis for estimation of shear capacity of FRP reinforced concrete members. Applied Soft Computing, 105, 107281. https://doi.org/10.1016/j.asoc.2021.107281
Go to original source...
- Dash, R. K., Nguyen, T. N., Cengiz, K., & Sharma, A. (2021). Fine-tuned support vector regression model for stock predictions. Neural Computing and Applications, 35(32), 23295-23309. https://doi.org/10.1007/s00521-021-05842-w
Go to original source...
- Divina, F., Gilson, A., Gómez-Vela, F., Torres, M., & Torres, J. F. (2018). Stacking Ensemble Learning for Short-Term Electricity Consumption Forecasting. Energies, 11(4), 949. https://doi.org/10.3390/en11040949
Go to original source...
- Gao, X., Shan, C., Hu, C., Niu, Z., & Liu, Z. (2019). An adaptive ensemble machine learning model for intrusion detection. IEEE Access, 7, 82512-82521. https://doi.org/10.1109/access.2019.2923640
Go to original source...
- Gohar, U., Biswas, S., & Rajan, H. (2023). Towards Understanding Fairness and its Composition in Ensemble Machine Learning. In 2023 IEEE/ACM 45th International Conference on Software Engineering (ICSE), (pp. 1533-1545). IEEE. https://doi.org/10.1109/ICSE48619.2023.00133
Go to original source...
- Hu, Y., Su, P., Hao, X., & Tang, F. (2009). The Long-Term Predictive Effect of SVM Financial Crisis Early-Warning Model. In 2009 IEEE First International Conference on Information Science and Engineering, (pp. 4573-4576). IEEE. https://doi.org/10.1109/ICISE.2009.1230
Go to original source...
- Huang Y., Deng C., Zhang X. and Bao Y. (2022). Forecasting of stock price index using support vector regression with multivariate empirical mode decomposition. Journal of Systems and Information Technology, 24(2), 75-95. https://doi.org/10.1108/jsit-12-2019-0262
Go to original source...
- Kenfack, P. J., Khan, A., Kazmi, S. M. A., Hussain, R., Oracevic, A., & Khattak, A. M. (2021). Impact of Model Ensemble On the Fairness of Classifiers in Machine Learning. In 2021 IEEE International Conference on Applied Artificial Intelligence (ICAPAI), (pp. 1-6). IEEE. https://doi.org/10.1109/ICAPAI49758.2021.9462068
Go to original source...
- Kumar G., Jain S., & Singh U. P. (2021). Stock market forecasting using computational intelligence: a survey. Archives of Computational Methods in Engineering, 28(3), 1069-1101. https://doi.org/10.1007/s11831-020-09413-5
Go to original source...
- Lin Y., Guo H., & Hu J. (2013). An SVM-based approach for stock market trend prediction. In 2013 IEEE International Joint Conference on Neural Networks (IJCNN), (pp. 1-7). IEEE. https://doi.org/10.1109/IJCNN.2013.6706743
Go to original source...
- Majhi, B., & Anish, C. (2015). Multiobjective optimization based adaptive models with fuzzy decision making for stock market forecasting. Neurocomputing, 167, 502-511. https://doi.org/10.1016/j.neucom.2015.04.044
Go to original source...
- Rubio, L., & Alba, K. (2022). Forecasting selected Colombian shares using a hybrid ARIMA-SVR model. Mathematics, 10(13), 2181. https://doi.org/10.3390/math10132181
Go to original source...
- Sharma D., Singla S. K., & Sohal A. K. (2021). Stock market prediction using ARIMA, ANN and SVR. In ICCCE 2020, (pp. 1081-1092). Springer. https://doi.org/10.1007/978-981-15-7961-5_100
Go to original source...
- Siddique M., Mohanty S., & Panda D. (2019). A hybrid model for forecasting of stock value of tata steel using orthogonal forward selection, support vector regression and teaching learning based optimization. Far East Journal of Mathematical Sciences, 113(1), 95-114. https://doi.org/10.17654/ms113010095
Go to original source...
- Singh, S., Madan, T. K., Kumar, J., & Singh, A. K. (2019). Stock market forecasting using machine learning: today and tomorrow. In 2019 IEEE 2nd International Conference on Intelligent Computing, Instrumentation and Control Technologies (ICICICT), (pp. 738-745). IEEE. https://doi.org/10.1109/ICICICT46008.2019.8993160
Go to original source...
- Snoek J., Larochelle H., & Adams R. P. (2012). Practical Bayesian optimization of machine learning algorithms. In 2021 ACM Proceedings of the 25th International Conference on Neural Information Processing Systems (NIPS'12), (pp. 2951-2959). ACM. https://dl.acm.org/doi/10.5555/2999325.2999464
- Thumu, S. R., & Nellore, G. (2021). Real-World Research Applications and Directions of Machine Learning Algorithms. Design Engineering, 2021(9), 14256-14275.
- Turner R., Eriksson D., McCourt M.J., Kiili J., Laaksonen E., Xu Z., & Guyon I. M. (2021). Bayesian Optimization is Superior to Random Search for Machine Learning Hyperparameter Tuning: Analysis of the Black-Box Optimization Challenge 2020. Proceedings of Machine Learning Research, 133, 3-26. http://proceedings.mlr.press/v133/turner21a/turner21a.pdf
- Virigineni, A., Tanuj, M., Mani, A., & Subramani, R. (2022). Stock forecasting using HMM and SVR. In 2022 IEEE International Conference on International Conference on Communication, Computing and Internet of Things, (pp. 1-7). IEEE. https://doi.org/10.1109/IC3IOT53935.2022.9767969
Go to original source...
- Wu J., Chen X. Y., Zhang H., Xiong L. D., Lei H., & Deng S. H. (2019). Hyperparameter optimization for machine learning models based on Bayesian optimization. Journal of Electronic Science and Technology, 17(1), 26-40. https://doi.org/10.11989/JEST.1674-862X.80904120
Go to original source...
- Yang, L., & Shami, A. (2020). On hyperparameter optimization of machine learning algorithms: Theory and practice. Neurocomputing, 415, 295-316. https://doi.org/10.1016/j.neucom.2020.07.061
Go to original source...
This is an open access article distributed under the terms of the Creative Commons Attribution 4.0 International License (CC BY 4.0), which permits use, distribution, and reproduction in any medium, provided the original publication is properly cited. No use, distribution or reproduction is permitted which does not comply with these terms.