Open Access Conference Proceedings

Quantitative forecasting methods based on the time series analysis have been most widely used in short-term demand forecasting thanks to the facts that they do not place high demands on time and finances, and that they are highly objective compared to qualitative forecasting methods. However, the success of demand forecasting depends on many other factors that are rarely mentioned in the literature. Based on the survey in a small manufacturing company, the paper focuses on the influence of temporal aggregation level on forecasting accuracy, and the specifics of small companies which have to deal with the insufficient technical support and sporadic demand. The paper aim is to analyse the forecasting accuracy of selected quantitative methods in relation to temporal aggregation level of forecasted demand and specify the application possibilities and limitations of the methods in the monitored company. The selected methods include the naïve method, the average method, the method of time series decomposition, the simple exponential smoothing method, the Holt’s linear trend method, the Brown’s linear trend method, the simple seasonal exponential smoothing method, the Holt-Winters trend and seasonal method. In-depth interviews with the managers of the company and time series analysis were used as research methods.

Keywords: demand forecasting, exponential smoothing, forecast accuracy, FMCG, quantitative methods

© This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.