The inventory cost of common mis-specification of demand-forecasting models

In inventory planning, the use of exponential smoothing to forecast demand or the assumption that demand over consecutive time periods is i.i.d. is commonplace. In practice, these forecasting approaches are often invoked without justifying their appropriateness. This paper asserts that, in many situations, the demand process may be different from that implicit in these commonly applied forecasting methods. In particular, it considers demand generated by a general ARMA process. For such a process, the paper derives expressions for the comparison of the steady-state sum of holding cost and stockout cost per unit time that results from using the correct forecasting model with that which results from the two commonly-used models mentioned above. This comparison indicates that correctly identifying the demand process is warranted and that popular efforts in batch-size reduction increase the benefits of doing so.