Abstract
As companies state that a delivery service is important to their customers, an out-of-stock is considered harmful and therefore they keep safety stock in case of uncertain demand. For decision making on the level of safety stock a complete formulation of the distributional form of the demand during lead time is required. In practice, this information may not be available. In such a case, only partial information on the distribution might be available, such as the range, the mode, the mean or the variance. Given a value for a service performance measure, the decision maker, in this case, is not confronted with a single value for the safety stock but rather with an interval. The present research shows how upper and lower bounds of the safety stock are obtained in an analytical way, given a pre-specified service level using a service performance measure, called ‘expected number of units short’. The technique is also illustrated and compared within the framework of the research.
Highlights
In the business world, investment in inventories might be very high
The authors of the present paper propose using a search procedure based on a linear programming approach
The research aims at proposing methods for obtaining a safety stock, given a customer service level, in a situation where the demand during lead time is not completely known
Summary
Investment in inventories might be very high. companies are confronted with fluctuations in inventories in time and with uncertainties both in demand and supply, which directly influence decisions on inventories. It is assumed that the demand follows a Normal distribution, so that, given a service level and the knowledge about the first two moments, the required safety stock can be determined. In. Janssens and Ramaekers’ research [6], an approach has been developed to obtain the reorder point based on the knowledge of the range, mean and variance of the demand distribution only, which is the same information as required for the use of the normal distribution (as many times used in commercial software). The present paper aims at investigating how such a distribution can be determined and which techniques are available to achieve it It would be outstanding if a set of analytical formulas were available to determine the safety stock, given the knowledge of range, mean and variance of the demand during lead time, with the constraint that the resulting distribution should be unimodal. Illustrations, opportunities and limitations of the use of the methods are provided for the unimodal case
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
