Forecasting the sales of an innovative agro-industrial product with limited information: A case of feta cheese from buffalo milk in Thailand

This research forecasts the sales of an innovative agro-industrial product, the feta cheese from buffalo milk, in Thailand using limited information from January 2000 to August 2012. It aims to find how much data sufficiently needed for the prediction of accurate sales concerning that newly launched products are likely to provide insufficient information for traditional statistical methods. Furthermore, it compares two forecasting models; the Bass model (Bass, 1969) and the Logistic function (Stoneman, 2010) in terms of Mean Absolute Percentage Error (MAPE). It estimates the models by maximum likelihood and least squares methods with quadratic interpolation and quasi-Newton in Matlab. The findings show that the sales can be accurately forecasted by using monthly information just only 7 months to 24 months after the launching of the product. A comparison of the Bass model and the Logistic function using the same estimation methods shows that the Logistic function is superior to Bass model when using the data in the range of 7 to 24 months. In addition, the study indicates that the predictive sales values of the Bass model are always lower than those of the Logistic function. When combining them together, the Bass model always predicts the Lower-bound of the sales whereas those of Logistic function predicts the upper-bound. The area between the upper and lower bounds constructs the possibility of the sales. Last, the study calculates how long the product will last in the market and predicts the maximum sales by intercepting the lines of both models with the OLS linear time trend.