The Comparison of Various Exponential Smoothing Models and their Significance in Modern Time Series Forecasting
Article Sidebar
Main Article Content
Abstract
Exponential Smoothing model is one of the most used forecasting models in modern time series forecasting. This is a technique which is applied to time series data particularly with seasonality, used to yield smoothed data for presentation and or to make forecasts. Exponential smoothing models have been found to be amongst the most effective forecasting models mostly used for linear seasonal data series. It is made up of three types namely Simple exponential smoothing (Type I) which is used when the time series has no trend, Double exponential smoothing (Type II) which is used in handling a time series that displays a slowly changing linear trend and the third is winters’ exponential smoothing method (Type III), used in predicting seasonal data. It is a powerful forecasting method which can be used as an alternative to the popular Box-Jenkins ARIMA methods. It also produces accurate and reliable forecasts which predict for the future. The forecasts show projected and actual demand which allows demand planning to be done effectively. The better the analysis of the main characteristics of the time series, the more accurate the exponential smoothing forecasts are likely to be. Exponential smoothing is easy to understand and apply; what is needed in this method are the forecast for the latest time period and relevant parameter constants such as , and which are associated with the level, trend and seasonality respectively.
Downloads
Article Details
References
Brown, R. G., (1962). Smoothing, forecasting and prediction of discrete time series. Prentice- Hall.
Brown, R. G. (1959). Statistical Forecasting for Inventory Control. New York: McGraw-Hill.
Dawson, C. W., Abrahart, R. J., & See, L. M. (2007). HydroTest: A web-based toolbox of evaluation metrics for the standardised assessment of hydrological forecasts. Environmental Modelling and Software, 22(7), 1034–1052. https://doi.org/10.1016/j.envsoft.2006.06.008
Gardner, E.S. & McKenzie, E. (1985). Forecasting trends in time series, Management Science, 31, 1237-1246.
Gardner, E.S. & McKenzie, E. (1988). Model identification in exponential smoothing, Journal of the Operational Research Society, 39, 863-867.
Gardner, E. S. (1987). Smoothing methods for short-term planning and control. In S. Makridakis & S. C. Wheelwright (Eds.). The handbook of forecasting – a manager’s guide, (pp. 174-175). New York: John Wiley & Sons.
Holt, C. C. (1957). Forecasting trends and seasonal by exponentially weighted averages, O.N.R. Memorandum 52/1957, Carnegie Institute of Technology.
Hyndman, R. J., Koelher, A. B., Ord, J. K., & Snyder, R. D. (2008). Forecasting with exponential Smoothing – The State Space Approach. Berlin: Springer.
Hyndman, R. J. (2014). Initializing the Holt-Winters method. In Hyndsight – A blog by R. J.
Hyndman. Retrieved March 10, 2014 from http://robjhyndman.com/hyndsight/hw-initialization/.
Hyndman, L. R. J. (2014). Forecasting : Principles & Practice. September.
Kalekar, P. S., & Bernard, P. (2004). Time series Forecasting using Holt-Winters Exponential Smoothing Under the guidance of. 04329008, 1–13.
Kalinova, M. (n.d.). Exponential forecasting of the monthly volume of the tourism receipts in Bulgaria. m(1).
Makatjane, K. D., & Moroke, N. D. (2016). Comparative study of holt-winters triple exponential smoothing and seasonal arima : forecasting short term seasonal car sales in south africa. 6(1), 71–82.
Rahman, H., Salma, U., & Hossain, M. (2016). Revenue Forecasting using Holt – Winters Exponential Smoothing. December.
Rangamati, R., & Ahmed, F. (2018). Application of ARIMA Models in Forecasting Monthly Total Application of ARIMA Models in Forecasting Monthly Total Rainfall of Rangamati , Bangladesh. September.
Shcherbakov, M. V., & Brebels, A. (2013). A Survey of Forecast Error Measures. 24(4), 171–176. https://doi.org/10.5829/idosi.wasj.2013.24.itmies.80032
Smyl, S. (2019). A hybrid method of Exponential Smoothing and Recurrent Neural Networks for time series forecasting. July. https://doi.org/10.1016/j.ijforecast.2019.03.017
Sulandari, W., & Utami, H. (2016). Forecasting electricity load demand using hybrid exponential smoothing-artificial neural network model. 2(3), 131–139.
Supriatna, A., Susanti, D., & Hertini, E. (2017). Application of Holt exponential smoothing and ARIMA method for data population in West Java Application of Holt exponential smoothing and ARIMA method for data population in West Java. https://doi.org/10.1088/1742-6596/755/1/011001
Uddin, S. M., Rahman, A., & Ansari, E. U. (2017). Comparison of some statistical forecasting techniques with gmdh predictor : a case study. M(December), 16–21.
Woschnagg, E., & Cipan, J. (2004). Evaluating Forecast Accuracy. 17.