Evaluation of sale forecasting methods : a case study

This study investigated forecasting accuracy for sales. Three quantitative and one qualitative forecasting techniques were tested and two combinational models were generated and evaluated. Three data sets, obtained from a market leader were used to forecast sales. The series represented monthly sales for three years. Three accuracy levels were employed in this study, these are: Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), and Root Mean Square Error (RMSE). Results indicated that the quantitative method outperformed the qualitative method; that combining two or more quantitative methods provide better forecasts than the individual methods; and that combining quantitative and qualitative methods provide more accurate forecasts than the individual qualitative method. Future studies should focus on the reasons for the differences in accuracy achieved by the different forecasting models. In addition, more quantitative and qualitative methods should be investigated using several companies from different industries