Comparative Analysis and Short Term Sales Forecasting for an Ethiopian Shoe Manufacturing Company

Abstract

Forecasts are a basic input in the decision processes of operations management because they provide information on future demand and to increase revenue. The main purpose of this paper was to compare three different quantitative forecasting methods and develop a monthly short term sales forecasting model specifically on shoes of A-Shoe Company, Addis Ababa, Ethiopia. Twelve months (December 2013 - November 2014) sales data (of different types of pair of shoes) was collected from the company. From quantitative forecasting methods, a time-series model, that is, moving average, weighted moving average, and exponential smoothing were used to predict monthly sales forecast for the month of December 2014. Trend equation was formulated by using the least square regression method; analysis was done along with standard error of estimate. Prediction interval limits at 95% level of confidence were calculated. Exponential smoothing forecasting method (with alpha value 0.1) was found to be fit when comparing different mean absolute deviation (MAD), mean squared error (MSE), and mean absolute percent errors (MAPE). The forecasted shoe sales value was found to be within the prediction interval limits. ANOVA results revealed that the calculated value of F (9.34) was less than the table value of F (10.04). Hence, the null hypothesis (b = 0) is accepted. The resulting forecasting method can be used to provide a framework to forecast sales, specifically for national and international products and can position an organization's manufacturing services by designing the manufacturing service.