Managing slow-moving item: a zero-inflated truncated normal approach for modeling demand.

摘要: This paper proposes a slow-moving management method for system using of intermittent demand per unit time and lead items in service enterprise inventory models. Our uses zero-inflated truncated normal statistical distribution, which makes it possible to model mixed distribution. We conducted numerical experiments based on an algorithm used forecast over fixed show that our proposed distributions improved the performance continuous review with shortages. evaluated multi-criteria elements (total cost, fill-rate, shortage quantity cycle, adequacy distribution demand) decision analysis Technique Order Preference by Similarity Ideal Solution (TOPSIS). confirmed comparison other commonly approaches such as simple exponential smoothing Croston's method. found interesting association between intermittency time, square root this same parameter reorder point decisions, could be explained classical multiple linear regression model. variability was positively related points. study examined illustrative example. suggested approach is original, valuable, and, case item companies, allows verification decision-making criteria.