Drvna Industrija (Dec 2012)
Choice of Quantitative Method for Forecasting of Parquet Sales
Abstract
Companies that cannot predict business forecasts for their sales always fi nd themselves in ambiguity. In this research we analyzed two quantitative methods that gave the best results for forecasting the sales: Holt-Winters method of exponent smoothing of higher orders and linear regression of the 1st order. The data for the implementation of these two methods were obtained in a wood company that deals with parquet sales. The data were gathered for parquet sales by month in the years 2000 to 2009. The calculations of sales forecasts enabled to compare both methods. On the basis of smaller deviations from data obtained, we determined the most appropriate method. We received the best result with the use of Holt-Winters multiplicative model of exponent smoothing of higher orders. Thus, according to this research, this method should be used for further forecasting of parquet sales in the analyzed wood company.