Global optimization of the supply chain costsc

Forecasting models are often based on methods using various smoothing techniques. All parameters used in these techniques are determined by minimizing the mean absolute error (MAE), the mean square error (MSE) or some other error measurements. In this paper we show that optimization of the forecasting model should not be treated apart from the inventory model in which we use calculated forecasts. Using global optimization and the Solver optimization tool, we show that initial and smoothing parameters in the forecasting model can be determined to minimize costs - a fact applicable also to other models and other fields.