Support Vector Regression Parameters Optimization using Golden Sine Algorithm and Its Application in Stock Market

Advances in Mathematical Finance and Applications

مقاله 14، دوره 7، شماره 2، تیر 2022، صفحه 477-487   

نوع مقاله: َApplied-Research Paper

شناسه دیجیتال (DOI): 10.22034/amfa.2021.1936352.1623

نویسندگان

Mohammadreza Ghanbari¹؛ Mahdi Goldani^{* 2}

¹Department of Mathematical Sciences, Sharif University of Technology, Tehran, Iran

²Department of Economics, Hakim Sabzevari university, Sabzevar 9617976487, Iran

چکیده

Stock price prediction is one of the most important concerns of stockholders. This prediction, independent of the method which is used or the assumptions which are applied, is welcomed and trusted if it can guarantee a high fitting. So due to the high performance prediction, using some complicated models as Machine Learning family such as Support Vector Regression (SVR) was recommended instead of older and lower performance approaches such as multiple discriminant technique. SVR model have achieved high performance on forecasting problems, however, its performance is highly dependent on the appropriate selection of SVR parameters. In this study, a novel GSA-SVR model based on Golden Sine Algorithm is presented. The performance of the proposed model is compared with eleven other meta-heuristic algorithms on some stocks from NASDAQ. The results indicate that the given model here is capable of optimizing the SVR parameters very well and indeed is one of the best models judged by both prediction performance accuracy and time consumption.

کلیدواژه‌ها

Golden Sine Algorithm؛ Meta-heuristics Optimization Algorithms؛ Parameter Tuning؛ Support Vector Regression؛ Time Series Prediction

مراجع

References

 

[1] Abarbanel, H., Analysis of observed chaotic data, Springer Science and Business Media, 2012.

 

[2] Chang, C.C., Lin, C., Libsvm J.,, A library for support vector machines, ACM transactions on intelligent systems and technology (TIST), 2011, 2, 27. Doi: 10.1145/1961189.1961199

 

 [3] Cao, W., Liu, X., and Ni, J., Parameter optimization of support vector regression using Henry gas solubility optimization algorithm, IEEE Access,2020, 8, P.88633-88642. Doi: 10.1109/ACCESS.2020.2993267

 

[4] Chen, Y., Yang, H., Multiscale recurrence analysis of long-term nonlinear and nonstationary time series, Chaos, Solitons and Fractals, 2012, 45, P.978–987. Doi: 10.1016/j.chaos.2012.03.013

                     

[5] Cortes, C., Vapnik, V., Support-vector networks, Machine learning, 1995, 20, P.273–297. Doi: 10.1007/BF00994018    

           

[6] Diebold, F.X., Mariano, R.S.: Comparing predictive accuracy, Journal of Business and economic statistics, 2002, 20, P.134–144. Doi: 10.1198/073500102753410444

 

[7] Ghanbari, M., Arian, H., Forecasting stock market with support vector regression and butterfly optimization algorithm, arXiv preprint arXiv, 2019,1905.11462.

 

[8] Huang, C.F., A hybrid stock selection model using genetic algorithms and support vector regression, Applied Soft Computing, 2012, 12, P.807–818. Doi:10.1016/j.asoc.2011.10.009

 

[9] Huang, C., Li, Y., and Yao, X., A survey of automatic parameter tuning methods for metaheuristics, IEEE transactions on evolutionary computation, 2019, 24, 2, P.201-216. Doi: 10.1109/TEVC.2019.2921598

 

[10] Kazemi, M.S., Banihabib, M.E., and Soltani, J., A hybrid SVR-PSO model to predict concentration of sediment in typical and debris floods, Earth Science Informatics, 2021, 14, 1, P.365-376. Doi: 10.1007/s12145-021-00570-0

 

[11] Keerthi, S.S., Sindhwani, V., Chapelle, O., An efficient method for gradient-based adaptation of hyperparameters in svm models, Advances in neural information processing systems, 2007, P.673–680.

 

[12] Kennel, M.B., Brown, R., Abarbanel, H.D., Determining embedding dimension for phase-space reconstruction using a geometrical construction, Physical review A, 1992, 45, 3403.

 Doi: 10.1103/PhysRevA.45.3403

 

[13] Li, S., Fang, H., Liu, X., Parameter optimization of support vector regression based on sine cosine algorithm, Expert systems with Applications, 2018, 91, P.63–77. Doi: 10.1016/j.eswa.2017.08.038

 

[14] Liu, M., Luo, K., Zhang, J., and Chen, S., A stock selection algorithm hybridizing grey wolf optimizer and support vector regression, Expert Systems with Applications, 2021, 179.  Doi: 10.1016/j.eswa.2021.115078

 

[15] Luo, Z., Hasanipanah, M., Bakhshandeh Amnieh, H., Brindhadevi, K., and Tahir, M.M., GA-SVR: a novel hybrid data-driven model to simulate vertical load capacity of driven piles, Engineering with Computers, 2021, 37(2), P.823-831. Doi: 10.1007/s00366-019-00858-2

 

[16] Malik, H., Iqbal, A., Joshi, P., Agrawal, S., and Bakhsh, F.I., eds., Metaheuristic and Evolutionary Computation: Algorithms and Applications, Springer Nature Singapore, 2021

 

[17] Rahmani, M., Khalili Eraq, M., Nikoomaram H., Portfolio Optimization by Means of Meta Heuristic

Algorithms, Advances in mathematical finance applications, 2019, 4, P.83-97.

 Doi: 10.22034/amfa.2019.579510.1144

 

[18] Sai, L., and Huajing, F., WOA-based algorithm for parameter optimization of support vector regression and its application to condition prognostics, In 2017 36th Chinese Control Conference (CCC), 2017, P.7345-7350, IEEE, Doi: 10.23919/ChiCC.2017.8028516

 

[19] Setiawan, I.N., Kurniawan, R., Yuniarto, B., Caraka, R.E., and Pardamean, B., Parameter Optimization of Support Vector Regression Using Harris Hawks Optimization, Procedia Computer Science, 2021,179, P.17-24. Doi: 10.1016/j.procs.2021.12.003

 

[20] Sun, Y., Ding, S., Zhang, Z. and Jia, W., An improved grid search algorithm to optimize SVR for prediction, Soft Computing, 2021, 25(7), P. 5633-5644. Doi: 10.1109/ICCT.2012.6511415

 

[21] Takens, F., Detecting strange attractors in turbulence, in: Dynamical systems and turbulence, Warwick 1980, Springer, P.366–381. Doi: 10.1007/BFb0091924

 

[22] Tanyildizi, E., Demir, G., Golden sine algorithm: a novel math-inspired algorithm, Advances in Electrical and Computer Engineering, 2017, 17, P. 71–79. Doi: 10.4316/AECE.2017.02010  

 

[23] Vapnik, V., The nature of statistical learning theory, Springer science and business media, 2013

 

[24] Wang, D., Lu, Y., Chen, B., and Zhao, Y., Wind weather prediction based on multi-output least squares support vector regression optimised by bat algorithm, International Journal of Embedded Systems, 2020, 12(2), P.137-145. Doi: 10.1504/IJES.2020.105936

 

[25] Wu, C.H., Tzeng, G.H., Lin, R.H., A novel hybrid genetic algorithm for kernel function and parameter optimization in support vector regression, Expert Systems with Applications, 2009, 36, P.4725–4735.

Doi: 10.1016/j.eswa.2008.06.046

 

[26] Yeh, C.Y., Huang, C.W., Lee, S.J., A multiple-kernel support vector regression approach for stock market price forecasting, Expert Systems with Applications, 2011, 38, P.2177–2186. Doi: 10.1016/j.eswa.2010.08.004

 

[27] Zanjirdar, M., Overview of Portfolio Optimization Models, Advances in mathematical finance and applications, 2020, 5(4), P.419-435, Doi: 10.22034/amfa.2020.1897346.1407 

 

[28] Zhang, J., Teng, Y.F., and Chen, W., Support vector regression with modified firefly algorithm for stock price forecasting, Applied Intelligence, 2019, 49(5), P.1658-1674. Doi: 10.1007/s10489-018-1351-7

 

[29] Zheng, J., Wang, Y., Li, S., and Chen, H., The Stock Index Prediction Based on SVR Model with Bat Optimization Algorithm, Algorithms, 2021, 14(10). Doi: 10.3390/a14100299

 

[30] Zhang, D., Xiang, W., Cao, Q., Chen, S., Application of incremental support vector regression based on optimal training subset and improved particle swarm optimization algorithm in real-time sensor fault diagnosis, Applied Intelligence, 2021, 51(6), P.3323-3338. Doi: 10.1007/s10489-020-01916-9