مقایسه روش رگرسیون بردار پشتیبان معمولی و گروهی برای پیش‌بینی قیمت سهام

حسینی, سیدمحمد; ابتیاع, مجید; آریافر, محمدرضا

doi:10.22052/scj.2025.255297.1260

مقایسه روش رگرسیون بردار پشتیبان معمولی و گروهی برای پیش‌بینی قیمت سهام

نوع مقاله : مقاله پژوهشی

نویسندگان

¹ گروه پژوهشی هوش مصنوعی گهر، دانشکده علوم پایه، دانشگاه آیت الله بروجردی (ره)، بروجرد، ایران.

² گروه اقتصاد، دانشکده علوم اداری و اقتصادی، دانشگاه فردوسی مشهد، مشهد، ایران.

10.22052/scj.2025.255297.1260

چکیده

انباشت سرمایه و نگهداری صحیح از دارایی نقش بسزایی را در رشد اقتصادی کشورها ایفا می‌کند. نقش موثر این عامل و اهمیت آن را به روشنی در سیستم اکثر کشورها به ویژه نظام‌های سرمایه‌داری می‌توان مشاهده نمود. بازار سرمایه یکی از مناسبترین جایگاه‌ها به منظور جذب دارایی‌های اندک و بکارگیری آنها با هدف رشد و ارتقا یک شرکت و همچنین افزایش دارایی شخصی سرمایه‌گذاران است. از اینرو، سرمایه‌گذاری درست، به افراد کمک می‌کند تا با مدیریت صحیح بخش مازاد درآمدهای خود، بتوانند به سرمایه لازم جهت رسیدن به اهداف خود دست پیدا کنند. اساسا قیمت سهام، غیرخطی و آشوبناک است، بنابراین سرمایه‌گذاری در بازار بورس، خطر بالایی به همراه دارد. برای به حداقل رساندن این خطر و کاهش مخاطرات، یک سیستم کارا مورد نیاز است که قادر باشد حرکت قیمت سهام در آینده را با دقت بالایی پیش‌بینی نماید. در این راستا، مدل‌های یادگیری ماشین عملکرد مناسبی در زمینه پیش‌بینی با دقت بالا را دارا هستند. الگوریتم‌های یادگیری ماشین توانایی مدل نمودن سیستم‌های غیرخطی و پیچیده را دارند. در این پژوهش به کمک رویکرد گروهی جدید مبتنی بر رگرسیون بردار پشتیبان یک مدل جمعی یا ترکیبی ساخته می‌شود که از دقت و سرعت بالایی در پیش‌بینی قیمت سهام برخوردار است. سهم‌های مورد استفاده در این پژوهش ده سهام شاخص‌ساز فولاد، شستا، فارس، فملی، شپنا، شتران، شبندر، خودرو، خساپا و پارس است که در بازه زمانی 1400/01/07 تا 1403/04/31 در نظر گرفته شده است. بر اساس معیارهای مختلف، نتایج به دست‌ آمده برتری روش رگرسیون بردار پشتیبان گروهی بر روش معمولی رگرسیون بردار پشتیبان و روش جنگل تصادفی را نشان می‌دهد.

کلیدواژه‌ها

موضوعات

یادگیری ماشین

عنوان مقاله [English]

Comparison of single and ensemble support vector regression models for stock price prediction

نویسندگان [English]

Sayyed Mohammad Hoseini ¹
Majid Ebtia ¹
Mohammad Reza Ariafar ²

¹ Gahar Artificial Intelligence Research Group, Faculty of Basic Sciences, Ayatollah Boroujerdi University , Boroujerd, Iran.

² Department of Economics, Faculty of Economics and Administrative Sciences, Ferdowsi University of Mashhad, Mashhad, Iran

چکیده [English]

Capital accumulation and proper asset management play a crucial role in the economic growth of countries. The significant impact of this factor, as well as its importance, can be clearly observed in the system of most countries, especially capitalist systems. The capital market is one of the most appropriate places to attract small assets and use them in order to grow and improve a company and also increase the personal assets of investors. Therefore, correct investment helps individuals to manage the surplus of their incomes properly, enabling them to attain the necessary capital to achieve their goals. Essentially, stock prices are nonlinear and chaotic; hence, investing in the stock market carries a high risk. To minimize this risk and reduce hazards, an efficient system is required that can predict future stock price movements with high accuracy. Given the importance of this issue, machine learning models have shown suitable performance in this area. Machine learning algorithms have the ability to model nonlinear and complex systems. In this research, a novel collective approach based on Support Vector Regression is used to construct a composite or hybrid model that enjoys high accuracy and speed in predicting stock prices. The stocks used in this research are the ten index-making shares of FOLD, TAMN, PKLJ, MSMI, PNES, PTEH, PNBA, IKCO, SIPA and PARS, considered in the period from 2021-03-27 to 2024-07-21. Based on various criteria, the results demonstrate the superiority of the collective Support Vector Regression method over the conventional Support Vector Regression method and the Random Forest approach.

کلیدواژه‌ها [English]

Machine learning
Support vector regression
Ensemble method
Stock market
Price prediction

مراجع

[1] R. Oprea and O. Stoica, “Capital Markets Integration and Economic Growth,” Montenegrin J. Econ., vol. 14, no. 3, pp. 23-35, 2018, doi: 10.14254/1800-5845/2018.14-3.2.
[2] M. Nooshyar and A. Ghasemi Marzbali, “Day-Ahead Electricity Price Forecasting by a New Hybrid Algorihtm Based on ELM, Curvelet Transform, Preprocessing System, and Modified VCS Algorithm,” Comput. Intell. Elect. Eng., vol. 10, no. 2, pp. 73-86, 2019, doi: 10.22108/isee.2019.116627.1215 [In Persian].
[3] S. Bajalan, S. Fallahpour, and N. Dana, “The Stock Trend Prediction Using Volume Weighted Support Vector Machine with a Hybrid Feature Selection Method to Predict the Stock Price Trend in Tehran Stock Exchange,” Financ. Manage. Strategy, vol. 4, no. 3, pp. 121-148, 2016, doi: 10.22051/jfm.2016.2575 [In Persian].
[4] H. R. Kordlouie and F. Teimouri, “Comparative Study of the Combination of Gaussian Models and Support Vector Machines in Detecting and Predicting Price Bubbles,” Financ. Eng. Portf. Manage., vol. 6, no. 23, pp. 79-104, 2015, dor: 20.1001.1.22519165.1394.6.23.5.3 [In Persian].
[5] Q. Ilyas, K. Iqbal, S. Ijaz, A. Mehmood, and S. Bhatia, “A Hybrid Model to Predict Stock Closing Price Using Novel Features and a Fully Modified Hodrick–Prescott Filter,” Electronics, vol. 11, no. 21, p. 3588, 2022, doi: 10.3390/electronics11213588.
[6] H. Huang, W. Zhang, G. Deng, and J. Chen, “Predicting Stock Trend Using Fourier Transform and Support Vector Regression,” in Proc. IEEE 17th Int. Conf. Comput. Sci. Eng. (CSE), 2014, pp. 213-216, doi: 10.1109/CSE.2014.70.
[7] S. A. Basher, A. A. Haug, and P. Sadorsky, “The impact of economic policy uncertainty and commodity prices on CARB country stock market volatility,” MPRA Paper 96577, Univ. Library of Munich, Germany, 2019. [Online]. Available: https://ideas.repec.org/p/pra/mprapa/96577.html
[8] N. Passalis, A. Tefas, J. Kanniainen, M. Gabbouj, and A. Iosifidis, “Temporal Bag-of-Features Learning for Predicting Mid Price Movements Using High Frequency Limit Order Book Data,” IEEE Trans. Emerg. Topics Comput. Intell., vol. 4, no. 6, pp. 774-785, 2020, doi: 10.1109/TETCI.2018.2872598.
[9] M. Obthong, N. Tantisantiwong, W. Jeamwatthanachai, and G. Wills, “A Survey on Machine Learning for Stock Price Prediction: Algorithms and Techniques,” in Proc. 12th Int. Joint Conf. Comput. Intell. (IJCCI), 2020, pp. 63-71, doi: 10.5220/0009340700630071.
[10] P. Sadorsky, “A Random Forests Approach to Predicting Clean Energy Stock Prices,” J. Risk Financ. Manage., vol. 14, no. 2, p. 48, 2021, doi: 10.3390/jrfm14020048.
[11] B. Eguz, F. E. Corbaci, and T. Kaya, “Stock Price Prediction of Turkish Banks Using Machine Learning Methods,” in Intelligent and Fuzzy Techniques for Emerging Conditions and Digital Transformation, C. Kahraman et al., Eds., vol. 308, Cham, Switzerland: Springer, 2022, pp. 222-229, doi: 10.1007/978-3-030-85577-2_26.
[12] P. Samad, S. Mutalib, and S. Rahman, “Analytics of Stock Market Prices Based on Machine Learning Algorithms,” Indones. J. Electr. Eng. Comput. Sci., vol. 16, no. 2, pp. 1050-1058, 2019, doi: 10.11591/ijeecs.v16.i2.pp1050-1058.
[13] H. Liu, L. Qi, and M. Sun, “Short-Term Stock Price Prediction Based on CAE-LSTM Method,” Wireless Commun. Mobile Comput., vol. 2022, p. 4809632, 2022, doi: 10.1155/2022/4809632.
[14] Z. Rustam and P. Kintandani, “Application of Support Vector Regression in Indonesian Stock Price Prediction with Feature Selection Using Particle Swarm Optimisation,” Modelling Simul. Eng., vol. 2019, p. 8962717, 2019, doi: 10.1155/2019/8962717.
[15] M. A. Monadi and A. Najafi, “A Prediction-Based Portfolio Optimization Model Using Support Vector Regression,” Financ. Eng. Portf. Manage., vol. 14, no. 55, pp. 252-270, 2023 [In Persian].
[16] B. Dehghan Khanghahi, J. Bahrisales, S. Jabbarzadeh Kangarlouie, and A. Ashtab, “The Comparative Study of the Accuracy of Prediction of Support Vector Machine, Bayesian Network and C5 Models in Prediction Underpricing for Listed Companies at TSE and OTC,” Financ. Eng. Portf. Manage., vol. 11, no. 44, pp. 95-113, 2020, dor: 20.1001.1.22519165.1399.11.44.5.0 [In Persian].
[17] A. Khosravinejad and M. Shabani Sadr Pisheh, “Evaluation of Linear and Non-linear Models in Predicting the Stock Price Index in Tehran Stock Exchange,” Financ. Econ., vol. 8, no. 27, pp. 51-64, 2014, dor: 20.1001.1.25383833.1393.8.27.4.2 [In Persian].
[18] S. A. Monadjemi, M. Abzari, and A. Rayati Shavazi, “Modeling of Stock Price Forecasting in Stock Exchange Market, using Fuzzy Neural Networks and Genetic Algorithms,” J. Quant. Econ. (JQE), vol. 6, no. 3, pp. 1-26, 2009 [In Persian], doi: 10.22055/jqe.2009.10697 [In Persian].
[19] M. Ramazani and A. Ameli, “Forecasting of Stock Price Using Fuzzy Neural Network Based on GA and Compaision with Fuzzy Neural Network,” Econ. Modeling Res., vol. 6, no. 22, pp. 61-91, 2015, doi: 10.18869/acadpub.jemr.6.22.61 [In Persian].
[20] M. Zamani, A. Afsar, S. V. Saghafi, and A. Bayat, “An Expert System for Stock Price Prediction and Portfolio Optimization Using Fuzzy Neural Networks, Fuzzy Modeling, and Genetic Algorithms,” Financ. Eng. Portf. Manage., vol. 5, no. 21, pp. 107-130, 2014, dor: 20.1001.1.22519165.1393.5.21.7.4 [In Persian].
[21] I. Nti, A. Adekoya, and B. Weyori, “Efficient Stock-Market Prediction Using Ensemble Support Vector Machine,” Open Comput. Sci., vol. 10, no. 1, pp. 154-163, 2020, doi: 10.1515/comp-2020-0199.
[22] A. Li, Q. Wei, Y. Shi, and Z. Liu, “Research on Stock Price Prediction from a Data Fusion Perspective,” Data Sci. Finance Econ., vol. 3, no. 3, pp. 230-250, 2023, doi: 10.3934/DSFE.2023014.
[23] F. Kalhori and S. M. Hoseini, “Clustering of the Stock Price Using Minimum Spanning Tree,” Soft Comput. J., vol. 14, no. 1, pp. 72-87, 2025, doi: 10.22052/scj.2024.253526.1183 [In Persian].
[24] M. Ebtia, S. M. Hoseini, and R. Khochiani, “Credit Rating of Bank Customers Using a New Ensemble Method Based on Support Vector Machine: A Case Study of Pasargad Bank,” Soft Comput. J., vol. 10, no. 2, pp. 2-15, 2022, doi: 10.22052/scj.2022.243227.1016 [In Persian].
[25] S. M. Hoseini, M. Ebtia, and R. Khochiani, “An Ensemble Method Based on Bagging SVM for Credit Rating Problem,” Soft Comput. J., Accepted, 2024, doi: 10.22052/scj.2024.246330.1063 [In Persian].
[26] A. Smola and B. Scholkopf, “A Tutorial on Support Vector Regression,” Statist. Comput., vol. 14, no. 3, pp. 199-222, 2004, doi: 10.1023/B:STCO.0000035301.49549.88.
[27] M. Sedighi, H. Jahangirnia, M. Gharakhani, and S. Farahani Fard, “A Novel Hybrid Model for Stock Price Forecasting Based on Metaheuristics and Support Vector Machine,” Data, vol. 4, no. 2, p. 75, 2019, doi: 10.3390/data4020075.