ABSTRACT
Weighted Exponential Moving Average (WEMA) method is a new hybrid moving average method which combines the weighting factor calculation found in Weighted Moving Average method with Exponential Moving Average method. It had been proven on previous study that the method can give a better accuracy and robustness levels compared to other conventional moving average methods. Another study which combined the Weighted Moving Average method with Brown's Double Exponential Smoothing method had also been done. The proposed method is known as Brown's Weighted Exponential Moving Average (B-WEMA) method and had been proven to excel other conventional moving average methods in terms of the accuracy and robustness levels. In this study, we will try to compare WEMA and B-WEMA forecasting methods in time series analysis, especially in forecasting. We will implement both methods to forecast three major foreign exchange (forex) data transactions and compare the performance of both methods by using Mean Square Error and Mean Absolute Percentage Error criteria. From the experiments taken, it can be concluded that WEMA and B-WEMA have quite the same accuracy and robustness levels due to their slightly same MSE and MAPE values.
- Brockwell, P.J. and Davis, R.A. 2002. Introduction to Time Series and Forecasting, 2nd ed. Springer-Verlag, New York, 1--2.Google Scholar
- Dufour, J-M. 2008. Introduction to Time Series Analysis. Research Paper. McGill University, Canada.Google Scholar
- NIST/SEMATECH e-Handbook of Statistical Methods. Introduction to Time Series Analysis {Online}, retrieved on February 27, 2016. Available: http://www.itl.nist.gov/div898/handbook/pmc/section4/pmc41.htm.Google Scholar
- Subanar and Suhartono. 2009. Wavelet Neural Networks untuk Peramalan Data Time Series Finansial. Program Penelitian Dasar Perguruan Tinggi. FMIPA Universitas Gadjah Mada, Yogyakarta.Google Scholar
- Boediono and Koster. 2001. Teori dan Aplikasi Statistika dan Probabilitas. PT. Remaja Rosdakarya, Bandung.Google Scholar
- Render, B., Stair Jr., R.M., and Hanna, M.E. 2003. Quantitative Analysis for Management, 8th ed. Pearson Education, Inc., New Jersey.Google Scholar
- Grebenkov, D.S. and Serror, J. 2014. Following a Trend with an Exponential Moving Average: Analytical Results for a Gaussian Model. Physica A, 394, 288--303.Google ScholarCross Ref
- Klinker, F. 2011. Exponential Moving Average versus Moving Exponential Average. Math. Semesterber, 58, 1, 97--107.Google ScholarCross Ref
- Abdullah, L. 2012. ARIMA Model for Gold Bullion Coin Selling Prices Forecasting. International Journal of Advances in Applied Sciences (IJAAS), 1, 4, 153--158.Google ScholarCross Ref
- Suparman and Doisy, M. 2014. Hierarchical Bayesian of ARMA Models using Simulated Annealing Algorithm. TELKOMNIKA, 12, 1, 87--96.Google ScholarCross Ref
- Alwee, R., Hj Shamsuddin, S.M., and Sallehuddin, R. 2013. Hybrid Support Vector Regression and Autoregressive Integrated Moving Average Models Improved by Particle Swarm Optimization for Property Crime Rates Forecasting with Economic Indicators. The Scientific World Journal, 2013.Google Scholar
- Fard, A.K. and Akbari-Zadeh, M-R. 2014. A Hybrid Method Based on Wavelet, ANN, and ARIMA Model for Short-term Load Forecasting. Journal of Experimental and Theoretical Artificial Intelligence, 26,2, 167--182.Google ScholarCross Ref
- Thakur, A., Kumar, S., and Tiwari, A. 2015. Hybrid Model of Gas Prediction using Moving Average and Neural Network. In Proceedings of 1st International Conference on Next Generation Computing Technologies (NGCT). Dehradun, 735--737.Google Scholar
- Hansun, S. 2013. A New Approach of Moving Average Method in Time Series Analysis. In Proceedings of the 2013 IEEE International Conference on New Media (CoNMedia). Indonesia, 1--4.Google ScholarCross Ref
- Hansun, S. 2014. A Novel Research of New Moving Average Method in Time Series Analysis. International Journal of New Media Technology, 1, 1,22--26.Google Scholar
- NIST/SEMATECH e-Handbook of Statistical Methods. Double Exponential Smoothing {Online}, retrieved on August 28, 2015. Available: http://www.itl.nist.gov/div898/handbook/pmc/section4/pmc433.htm.Google Scholar
- Hansun, S. 2016. A New Approach of Brown's Double Exponential Smoothing Method in Time Series Analysis. Balkan Journal of Electrical & Computer Engineering, 4, 2, 75--78.Google ScholarCross Ref
- Turn, J., Norton, P., and Wright, J.N. 2006. Management of Event Operations. Routledge, New York.Google Scholar
- Nau, R. Moving average and exponential smoothing models {Online}, retrieved on August 19, 2015. Available: http://people.duke.edu/~rnau/411avg.htm.Google Scholar
- Shcherbakov, M.V., Brebels, A., Shcherbakova, N.L., Tyukov, A.P., Janovsky, T.A., and Kamaev, V.A. 2013. A Survey of Forecast Error Measures. World Applied Sciences Journal 24, 171--176.Google Scholar
- Lawrence, K.D., Klimberg, R.K., and Lawrence, S.M. 2009. Fundamentals of Forecasting using Excel. Industrial Press, Inc., New York. Google ScholarDigital Library
- Hyndman, R.J. and Athanasopoulos, G. 2012. Forecasting: Principles and Practice {Online}, OTexts. Available: http://otexts.com/fpp.Google Scholar
- Forex Forum. GVI Forex Database: Free Forex Historical Data {Online}, retrieved on November 15, 2016 from http://www.global-view.com/forex-trading-tools/forex-history/index.html.Google Scholar
Recommendations
A Large Dimensional VAR Model with Time-Varying Parameters for Daily Forex Forecasting
AbstractEconomic and financial data is extremely volatile relative to the others especially in the time series data. Foreign Exchange market or forex data is one among the others. Despite the fact that it is still impossible to guarantee the profits from ...
Forecasting Thailand's rice export: Statistical techniques vs. artificial neural networks
Forecasting the international trade of rice is difficult because demand and supply are affected by many unpredictable factors (e.g., trade barriers and subsidies, agricultural and environmental factors, meteorological factors, biophysical factors, ...
Revisiting the Holt-Winters' Additive Method for Better Forecasting
Time series are one of the most common data types encountered by data scientists and, in the context of today's exponentially increasing data, learning how to best model them to derive meaningful insights is an important skill in the Big Data and Data ...
Comments