Improved of Forecasting Sea Surface Temperature based on Hybrid ARIMA and Support Vector Machines Models
DOI:
https://doi.org/10.11113/mjfas.v17n5.2356Keywords:
Accuracy, Forecasting, Hybrid, Sea Surface Temperature, SVMsAbstract
Forecasting is a very effortful task owing to its features which simultaneously contain linear and nonlinear patterns. The Autoregressive Integrated Moving Average (ARIMA) model has been one the most widely utilized linear model in time series forecasting. Unfortunately, the ARIMA model cannot effortlessly handle nonlinear patterns alone. Thus, Support Vector Machine (SVM) model is introduced to solve nonlinear behavior in the datasets with high variance and uncertainty. The purposes of this study are twofold. First, to propose a hybrid ARIMA models using SVM. Secondly, to test the effectiveness of the proposed hybrid model using sea surface temperature (SST) data. Our investigation is based on two well-known real datasets, i.e., SST (modis) and in-situ SST (hycom). Statistical measurement such as MAE, MAPE, MSE, and RMSE are carried out to investigate the efficacy of the proposed models as compared to the previous ARIMA and SVMs models. The empirical results reveal that the proposed models produce lesser MAE, MAPE, MSE, and RMSE values in comparison to the single ARIMA and SVMs models. In additional, ARIMA-SVM are much better than compared to the existing models since the forecasting values are closer to the actual value. Therefore, we conclude that the presented models can be used to generate superior predicting values in time series forecasting with a way higher forecast precision.
References
Muhamad Safiih, L, Nurul Hila, Z., Mohd Tajuddin, A., Vigneswary, P., Mohd Noor Afiq, R, Razak, Z., Md Suffian, I., and Idham,K., “Improving the Performance of ANN-ARIMA Models for Predicting Water Quality in the Offshore Area of Kuala Terengganu, Terengganu, Malaysia” Journal of Sustainability Science and Management, 13(1), 27-37, 2018.
Zhou, X., Pan, Z., Hu, G., Tang, S., and Zhao, C, “Stock Market Prediction on High-Frequency Data Using Generative Adversarial Nets”, Journal of Mathematical Problems in Engineering vol. 2018, 1–11, 2018.
Weng, B., Ahmed, M. A., and Megahed, F. M., “Stock market one-day ahead movement prediction using disparate data sources”, Journal of Expert Systems with Applications, 79, 153–163, 2018.
Kita, R., Yoshihara, A., Matsubara, T., and Uehara, K., “Deep learning for stock prediction using numerical and textual”, Journal of International Conference on Computer and Information Science (ICIS), pp. 2241-2891, 2016.
Checkley, M. S., Higón, D. A., and Alles, H., “The hasty wisdom of the mob: How market sentiment predicts stock market behavior”, Journal of Expert Systems with Applications, vol. 77, 256–263, 2017.
Shynkevich, Y., McGinnity, T. M., Coleman, S. A., and Belatreche, A., “Forecasting movements of health-care stock prices based on different categories of news articles using multiple kernel learning”, Journal of Decision Support Systems, vol 85, 74–83, 2016.
Al Wadi S., Mohd Tahir Ismail, M. H. Alkhahazaleh, and Samsul Ariffin Addul Karim.,”Selecting Wavelet Transforms Model in Forecasting Financial Time Series Data Based on ARIMA Model”, Journal of Applied Mathematical Sciences, 5(7), 315 – 326, 2011.
Fattah, J., Ezzine, L., Aman, Z., El Moussami, H. & Lachhab, A., “Forecasting of demand using ARIMA model”, International Journal of Engineering Business Management 10, 184797901880867, 2018.
Zhang, G., Eddy Patuwo, B., and Y. Hu, M., “Forecasting with artificial neural networks”, International Journal of Forecasting, 14(1), 35–62,1998.
Burbidge, R., Trotter, M., Buxton, B., and Holden, S., “Drug design by machine learning: support vector machines for pharmaceutical data analysis”, Journal of Computers & Chemistry, 26(1), 5–14, 2001.
Huang, W., Nakamori, Y. & Wang, S. Y., “Forecasting stock market movement direction with support vector machine”, Computers & Operations Research 32(10), 2513–2522, 2005.
Alaka, H. A., Oyedele, L. O., Owolabi, H. A., Kumar, V., Ajayi, S. O., Akinade, O.O., and Bilal,M. “Systematic review of bankruptcy prediction models: Towards a framework for tool selection” Journal of Expert Systems with Applications, 94,164–184, 2018.
Kim, K., “Financial time series forecasting using support vector machines”, Journal of Neurocomputing, 55(1-2), 307–319. 2003.
Shin, K.-S., Lee, T. S., and Kim, H. “An application of support vector machines in bankruptcy prediction model”, Journal of Expert Systems with Applications, 28(1), 127–135, 2005.
Sugumaran, V., Sabareesh, G., and Ramachandran, K., “Fault diagnostics of roller bearing using kernel-based neighborhood score multi-class support vector machine”, Journal of Expert Systems with Applications, 34(4), 3090–3098, 2008.
Makridakis, S., Andersen, A., Carbone, R., Fildes, R., Hibon, M., Lewandowski, R., and Winkler R. “The accuracy of extrapolation (time series) methods: Results of a forecasting competition”, Journal of Forecasting, 1(2), 111–153, 1982.
Pai, P.-F., and Lin, C.-S., “A hybrid ARIMA and support vector machines model in stock price forecasting”, International Journal of Management Science, 3(3), 497-505, 2005.
Huang, C.-L., and Tsai, C.-Y. “A hybrid SOFM-SVR with a filter-based feature selection for stock market forecasting”, Journal Expert Systems with Applications, 36(2), 1529–1539, 2009.
Ming W., Bao Y., Hu Z., and Xiong,T. Multistep-Ahead Air Passengers Traffic Prediction with Hybrid ARIMA-SVMs Models. The Scientific World Journal. 2014: 1-15. 2014.
Iturriaga L., F. J., and Sanz, I. P., “Bankruptcy visualization and prediction using neural networks: A study of U.S. commercial banks”, Journal of Expert Systems with Applications 42(6),2857–2869, 2015.
Weng, B., Ahmed, M. A., and Megahed, F. M., “Stock market one-day ahead movement prediction using disparate data sources”, Journal of Expert Systems with Applications, 79, 153–163, 2018.
Nurul Hila, Z, Muhamad Safiih, L., Maman Abdurachman, D., Fadhilah, Y., Mohd Noor Afiq, R., Aziz, D., Yahaya, I., Mohd Tajuddin, A. Improvement of time forecasting models using a novel hybridization of bootstrap and double bootstrap artificial neural networks. Applied Soft Computing. 84, 105-676. 2019.
McKenzie, E., “General exponential smoothing and the equivalent arma process”, Journal of Forecasting, 3(3), 333–344, 1984.
Hipel, K.W., and McLeod, A.I., “Time Series Modelling of Water Resources and Environmental Systems". Amsterdam, The Netherlands: Elsevier Science Publishers, 1994.
Cornillon P., Imam W., and Matzner E., “Forecasting time series using principal component analysis with respect to instrumental variables”, Journal of Computational Statistics & Data Analysis 52(3), 1269–1280, 2008.
Mohd Zamri, I., Roziah Zailan, Marzuki Ismail, and Muhamad Safiih, L., “Forecasting and Time Series Analysis of Air Pollutants in Several Area of Malaysia” American Journal of Environmental Sciences, 5(5), 625-632, 2009.
Rita, S., Yony, H., Rubiyanto, Fakhri, A.M., and Madzlan, A., “Multiple Linear Regression (MLR) Modeling of Wastewater in Urban Region of Southern Malaysia”, Journal of Sustainability Science and Management, 8(1), 93-102, 2013.
Mohd Zamri, I., Roziah Zailan., Marzuki Ismail, and Muhamad Safiih, L., “Time-series Analysis of Pollutants in East Coast Peninsular Malaysia”, Journal of Sustainability Science and Management, 5(1), 57-65, 2010.
Muhamad Safiih, L., Nurul Hila, Z., Mohd Noor Afiq, R., Muhamad Na’eim, A.R, and Mohd Tajuddin A., “Improvement of Estimation Based on Small Number of Events Per Variable (EPV) using Bootstrap Logistics Regression Model. Malaysian”, Journal of Fundamental and Applied Sciences, 13(4), 693-704, 2017a.
M. Z. Ibrahim, R. Zailan, M.Ismail and M.S. Lola (2010),Time-series Analysis of Pollutants in East Coast Peninsular Malaysia, Journal of Sustainability Science and Management, 5(1): 57-65.
Syerrina, Z. Naeim, A.R. Muhamad Safiih L.and Nuredayu, Z., “Explorative Spatial Analysis of Coastal Community Incomes in Setiu Wetlands: Geographically Weighted Regression”, International Journal of Applied Engineering Research, 12 (18), 7392-7396, 2017.
Muhamad Safiih, L, Nurul Hila, Z. Mohd Noor Afiq, R, Hizir, S., “Double Bootstrap Control Chart for Monitoring SUKUK Volatility at Bursa Malaysia”, Jurnal Teknologi, 79 (6), 149-157, 2017b.
Vapnik, V.N., “The Nature of Statistical Learning Theory”, New York, Springer, 1995.
Zhang, G. P., “Time series forecasting using a hybrid ARIMA and neural network model”, Journal of Neurocomputing, 50,159–175, 2003.
Metzger, E. J., and H. E. Hurlburt, The nondeterministic nature of Kuroshio penetration and eddy shedding in the South China Sea, J. Phys. Oceanogr, 31, 1712–1732, 2001.
Bleck, R., “An oceanic general circulation model framed in hybrid isopycnic-Cartesian coordinates”, Ocean Modelling, 4(1), 55–88, https://doi.org/10.1016/S1463-5003(01)00012-9, 2002.
