Augmented Winter’s method for forecasting under asynchronous seasonalities

作     者：Oktay Karabag MMurat Fadıloglu 

作者机构：School of EconomicsErasmus University RotterdamRotterdamThe Netherlands Department of Industrial EngineeringAmerican University of the Middle EastEgailaKuwait 

出 版 物：《Journal of Management Analytics》 (管理分析学报（英文）)

年 卷 期：2021年第8卷第1期

页      面：19-35页

核心收录：

学科分类：08[工学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：We would like to thank the reviewers for their constructive feedback that helped us to improve the manuscript 

主　　题：sales forecasting Ramadan effect asynchronous calendar effects exponential smoothing 

摘      要：The method of Winters(1960)is one of the most well-known forecasting methodologies in *** main reason behind its popularity is that it is easy to implement and can give quite effective and efficient results for practice ***,this method is not capable of capturing a pattern being emerged due to the simultaneous effects of two different asynchronous calendars,such as Gregorian and *** adapt this method in a way that it can deal with such patterns,and study its performance using a real dataset collected from a brewery factory in *** the same data set,we also provide a comparative performance analysis between our model and several forecasting models such as Winter’s(Winters 1960),TBAT(De Livera et al.2011),ETS(Hyndman et al.2002),and ARIMA(Hyndman and Khandakar 2008).The results we obtained reveal that better forecasts can be achieved using the new method when two asynchronous calendars exert their effects on the time-series.