The method of Winters (1960) is one of the most well-known forecasting methodologies in practice. The main reason behind its popularity is that it is easy to implement and can give quite effective and efficient results for practice purposes. However, 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 Hijri. We 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 Turkey. With 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.

asynchronous calendar effects, exponential smoothing, Ramadan effect, sales forecasting
dx.doi.org/10.1080/23270012.2020.1839362, hdl.handle.net/1765/132590
Journal of Management Analytics
Erasmus School of Economics

Karabağ, O. (Oktay), & Fadıloğlu, M.M. (M. Murat). (2020). Augmented Winter's method for forecasting under asynchronous seasonalities. Journal of Management Analytics. doi:10.1080/23270012.2020.1839362