Second-order System of Exponential Smoothing in Forecast for Drug Demand

Abstract

Demand for drugs at hospitals, under the inevitable effect of various uncertain factors, shows constant fluctuations. Therefore, in the inventory control of drugs, the forecast for demand has a close relation with the inventory levels. The exponential smoothing, as the extension of the weighted method of moving average, is practically very useful, for example, for the adjustment of the rate of response to the changes in demand. We have applied the second-order system of exponential smoothing in the forecast of the linear model demand in the inventory control of drugs. “ The sum of the absolute value of the forecast errors” and “the absolute value of the running sum of the forecast errors” were calculated. Then, regarding their ranking as the minus points, the 2 smoothing systems were evaluated by adding up those points. In consequence, it was found out that the first-order system of smoothing is apt to cause delayed response and that the second-order system of exponential smoothing may enable to make more accurate estimation of the expected demand.