Metaheuristic-Based Support Vector Machines for Exchange Rate Forecasting

Metaheuristic-Based Support Vector Machines for Exchange Rate Forecasting

  IJRES-book-cover  International Journal of Recent Engineering Science (IJRES)          
  
© 2024 by IJRES Journal
Volume-11 Issue-2
Year of Publication : 2024
Authors : Sudersan Behera
DOI : 10.14445/23497157/IJRES-V11I2P105

How to Cite?

Sudersan Behera, "Metaheuristic-Based Support Vector Machines for Exchange Rate Forecasting ," International Journal of Recent Engineering Science, vol. 11, no. 2, pp. 31-38, 2024. Crossref, https://doi.org/10.14445/23497157/IJRES-V11I2P105

Abstract
Given the dynamic and complex landscape of financial markets, accurately predicting financial time series presents considerable hurdles. This research explores the utilization of an evolutionary approach called Particle Swarm Optimization (PSO) to fine-tune the biases and weights of Support Vector Machine (SVM) models. This novel methodology leads to the development of an SVM-PSO hybrid model crafted through meticulous optimization strategies. This research evaluates the effectiveness of SVM-PSO by forecasting the final values of two prominent currency exchange rates. Additionally, this research constructs two comparative models, SVM-GD and SVM-GA, by training an equivalent SVM model using GD and GA techniques. The performances of all the models are gauged by RMSE and MSE metrics. Our results indicate that SVM-PSO surpasses SVM-GD in accuracy, representing a significant leap forward. This underscores the potency of the evolutionary PSO algorithm in tackling the intricacies inherent in time series forecasting for exchange rates.

Keywords
PSO, SVM, Metaheuristic algorithm, Financial Time series forecasting, Exchange rate forecasting.

Reference
[1] James B. McDonald, “Partially Adaptive Estimation of ARMA Time Series Models,” International Journal of Forecasting, vol. 5, no. 2, pp. 217–230, 1989.
[CrossRef] [Google Scholar] [Publisher Link]
[2] Jorge Ludlow, and Walter Enders, “Estimating Non-Linear ARMA Models using Fourier Coefficients,” International Journal of Forecasting, vol. 16, no. 3, pp. 333–347, 2000.
[CrossRef] [Google Scholar] [Publisher Link]
[3] Yushu Shao, “Prediction of Moderna Adjusted Closing Stock Price Trend Using ARIMA Model,” 2 nd International Conference on Finance, Investment and Business Analysis, vol. 44, pp. 108–114, 2023.
[CrossRef] [Publisher Link]
[4] Rahul Mangalampalli et al., “Stock Prediction Using Hybrid ARIMA and GRU Models,” International Journal of Engineering Research and Technology, vol. 9, no. 5, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[5] Mohammad Bagher Menhaj, Computational Intelligence, AmirKabir University of Technology (in persian), 2009.
[6] Jun Liu et al., “Prediction of Autogenous Shrinkage of Concretes by Support Vector Machine,” International Journal of Pavement Research and Technology, vol. 9, no. 3, pp. 169–177, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Wenjian Wang, Changqian Men, and Weizhen Lu, “Online Prediction Model Based on Support Vector Machine,” Neurocomputing, vol. 71, no. 4-6, pp. 550–558, 2008.
[CrossRef] [Google Scholar] [Publisher Link]
[8] L.M. Marangon Lima, E. Popova, and P. Damien, “Modeling and Forecasting of Brazilian Reservoir Inflows via Dynamiclinear Models,” International Journal of Forecasting, vol. 30, no. 3, pp. 464–476, 2014.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Roohollah Noori et al., “Comparison of ANN and Principal Component Analysis-Multivariate Linear Regression Models for Predicting the River Flow Based on Developed Discrepancy Ratio Statistic,” Expert Systems with Applications, vol. 37, no. 8, pp. 5856–5862, 2010.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Mohammed Akour, Mamdouh Alenezi, and Hiba Alsghaier, “Software Refactoring Prediction Using SVM and Optimization Algorithms,” Processes, vol. 10, no. 8, pp. 1-10, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[11] Qian Cao, “An Enterprise Financial Data Leakage Risk Prediction Based on ARIMA-SVM Combination Model,” International Journal of Applied Systemic Studies, vol. 1, no. 1, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Sijun Chen, “Breast Cancer Prediction Based on RF-SVM,” Applied and Computational Engineering, vol. 8, no. 1, pp. 657–666, 2023.
[CrossRef] [Publisher Link]
[13] Tianji Dai et al., “ICS-SVM: A User Retweet Prediction Method for Hot Topics Based on Improved SVM,” Digital Communications and Networks, vol. 8, no. 2, pp. 186–193, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[14] Ike Fitriyaningsih , and Yuniarta Basani, “Flood Prediction with Ensemble Machine Learning using BP-NN and SVM,” Journal of Technology and Computer Systems, vol. 7, no. 3, pp. 93–97, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[15] Min-Wei Huang et al., “SVM and SVM Ensembles in Breast Cancer Prediction,” PLOS ONE, vol. 12, no. 1, pp. 1-14, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[16] Ying Huang, “Improved SVM-Based Soil-Moisture-Content Prediction Model for Tea Plantation,” Plants, vol. 12, no. 12, pp. 1-16, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[17] Haoyu Ji, “Stock Price Prediction Based on SVM, LSTM, ARIMA,” International Conference on Portfolios, Global Marketing and Economic Environment, vol. 35, pp. 267–272, 2022.
[CrossRef] [Publisher Link]
[18] Ruichen Liu, Yinxi Li, and Mengdan Li, “Result Prediction of Wordle Word Guessing Game Based on SVM And BP Neural Network Multi-Input-Multi-Output Regression Prediction Model,” Highlights in Science, Engineering and Technology, vol. 70, pp. 175–182, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[19] Mohammad Nobarinia et al., “Dam Failure Peak Outflow Prediction through GEP-SVM Meta Models and Uncertainty Analysis,” Water Supply, vol. 21, no. 7, pp. 3387–3401, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[20] Sandeep Samantaray, Abinash Sahoo, and Ankita Agnihotri, “Prediction of Flood Discharge Using Hybrid PSO-SVM Algorithm in Barak River Basin,” MethodsX, vol. 10, pp. 1-21, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[21] Sandeep Samantaray, Abinash Sahoo, and Deba Prakash Satapathy, “Prediction of Groundwater-Level Using Novel SVM-ALO, SVM-FOA, and SVM-FFA Algorithms at Purba-Medinipur, India,” Arabian Journal of Geosciences, vol. 15, no. 8, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[22] Permit Mathuhu Sekatane, and Pitshou Bokoro, “Partial Discharge Localization through k-NN and SVM,” Energies, vol. 16, no. 21, pp. 1-16, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[23] Haiyan Sun et al., “Hybrid SVM and ARIMA Model for Failure Time Series Prediction based on EEMD,” International Journal of Performability Engineering, vol. 15, no. 4, pp. 1161-1170, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[24] Kai Tang, “Financial Time Series Prediction Based on EMD-SVM,” International Conference on Financial Market and Enterprises Management Engineering, vol. 30, pp. 218–227, 2022.
[CrossRef] [Publisher Link]
[25] Chenguang Yan, “Stock Price Prediction of Walmart Based on Combination of SVM and LS-SVM Models,” International Conference on Economics, Mathematical Finance and Risk Management, vol. 38, pp. 363–371, 2023.
[CrossRef] [Publisher Link]
[26] Xu Yanling, Wu Baolin, and Yang Liushan, “A Network-Adapative SVC Streaming Strategy with SVM-Based Bandwidth Prediction,” International Journal of Future Computer and Communication, vol. 3, no. 3, pp. 205–209, 2014.
[CrossRef] [Google Scholar] [Publisher Link]
[27] Jian Zhou et al., “Performance Evaluation of Rockburst Prediction Based on PSO-SVM, HHO-SVM, and MFO-SVM Hybrid Models,” Mining, Metallurgy & Exploration, vol. 40, pp. 617-635, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[28] Shiyu Zhou et al., “Prediction of the Ground Temperature with ANN, LS-SVM and Fuzzy LS-SVM for GSHP Application,” Geothermics, vol. 84, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[29] A.S. Babu, and S.K. Reddy, “Exchange Rate Forecasting Using ARIMA, Neural Network and Fuzzy Neuron,” Journal of Stock & Forex Trading, vol. 4, no. 3, pp. 1-5, 2015.
[Google Scholar] [Publisher Link]
[30] Hojin Lee, “Forecasting Performance of Asymmetric GARCH Stock Market Volatility Models,” SSRN Electronic Journal, vol. 13, no. 2, pp. 109-143, 2009.
[CrossRef] [Google Scholar] [Publisher Link]
[31] Xiangyu Zong, “MLP, CNN, LSTM and Hybrid SVM for Stock Index Forecasting Task to INDU and FTSE100,” SSRN Electronic Journal, pp. 1-37, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[32] D. Hercog, “Generalised Sliding Window Protocol,” Electronics Letters, vol. 38, no. 18, pp. 1067-1068, 2002.
[CrossRef] [Google Scholar] [Publisher Link]
[33] Sarat Chandra Nayak, “Development and Performance Evaluation of Adaptive Hybrid Higher Order Neural Networks for Exchange Rate Prediction,” International Journal of Intelligent Systems and Applications, vol. 9, no. 8, pp. 71–85, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[34] Sarat Chandra Nayak, Satchidananda Dehuri, and Sung-Bae Cho, “Intelligent Financial Forecasting with an Improved Chemical Reaction Optimization Algorithm Based Dendritic Neuron Model,” IEEE Access, vol. 10, pp. 130921–130943, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[35] S. Chakravarty et al., “An Evolutionary Functional Link Neural Fuzzy Model for Financial Time Series Forecasting,” International Journal of Applied Evolutionary Computation, vol. 2, no. 3, pp. 39–58, 2011.
[CrossRef] [Google Scholar] [Publisher Link]
[36] Vladimir N. Vapnik, The Nature of Statistical Learning Theory, Springer New York, 1995.
[Google Scholar] [Publisher Link]
[37] John G. Vlachogiannis, and Kwang Y. Lee, “Multi-Objective Based on Parallel Vector Evaluated Particle Swarm Optimization for Optimal Steady-State Performance of Power Systems,” Expert Systems with Applications, vol. 36, no. 8, pp. 10802–10808, 2009.
[CrossRef] [Google Scholar] [Publisher Link]
[38] Sandeep Samantaray, and Abinash Sahoo, “Estimation of Runoff through BPNN and SVM in Agalpur Watershed,” Frontiers in Intelligent Computing: Theory and Applications, pp. 268–275, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[39] Sandeep Samantaray, and Abinash Sahoo, “Assessment of Sediment Concentration through RBNN and SVM-FFA in Arid Watershed, India,” Smart Intelligent Computing and Applications, pp. 701–709, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[40] Weizhen Lu et al., “Air Pollutant Parameter Forecasting Using Support Vector Machines,” Proceedings of the 2002 International Joint Conference on Neural Networks, Honolulu, HI, USA, pp. 630–635, 2002.
[CrossRef] [Google Scholar] [Publisher Link]
[41] R. Salat, and S. Osowski, “Accurate Fault Location in the Power Transmission Line Using Support Vector Machine Approach,” IEEE Transactions on Power Systems, vol. 19, no. 2, pp. 979-986, 2004.
[CrossRef] [Google Scholar] [Publisher Link]
[42] J. Kennedy, and R. Eberhart, “Particle Swarm Optimization,” Proceedings of ICNN’95-International Conference on Neural Networks, Perth, WA, Australia, vol. 4, pp. 1942–1948, 1995.
[CrossRef] [Google Scholar] [Publisher Link]
[43] Shun-Ichi Amari, “Backpropagation and Stochastic Gradient Descent Method,” Neurocomputing, vol. 5, no. 4–5, pp. 185–196, 1993.
[CrossRef] [Google Scholar] [Publisher Link]
[44] Guo Zhiqiang, Wang Huaiqing, and Liu Quan, “Financial Time Series Forecasting Using LPP and SVM Optimized By PSO,” Soft Computing, vol. 17, no. 5, pp. 805–818, 2013.
[CrossRef] [Google Scholar] [Publisher Link]
[45] John H. Holland, Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence, The MIT Press, 1992.
[CrossRef] [Google Scholar] [Publisher Link]
[46] Muhammad Latif, and Sri Herawati, “Combined EEMD and ANN Improved by GA for Tourist Visit Forecasting,” Bulletin of Electrical Engineering and Informatics, vol. 11, no. 2, pp. 947–954, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[47] K. Sudha, Neeraj Kumar, and Poras Khetarpal, “GA-ANN Hybrid Approach for Load Forecasting,” Journal of Statistics and Management Systems, vol. 23, no. 1, pp. 135–144, 2020.
[CrossRef] [Publisher Link]