Augmented winter's method for forecasting under asynchronous seasonalities

In the manufacturing systems, demand forecasting is indispensable for the management activities such as procurement decisions, production planning and inventory management and so on. Therefore, various forecasting methods have been developed so far. In this study, Holt (2004) and Winters (1960) methods, which are well-known and easy to apply for the demand forecasting, are firstly investigated. These methods are not sufficient to capture demand pattern when the simultaneous effects of two different asynchronous calendars, such as Gregorian and Hijri, manifest themselves on the data. For this reason, Winter's method is extended by adding a new term which captures the joint effects of two asynchronous calendars. The new method is called as Augmented Winters method, and it is compared with the two classical methods by using a real data set which is collected from a brewery factory in Turkey. The obtained results indicate that better forecasts can be achieved using the new method when two asynchronous calendars exert their effects on the time-series.