Challenges in modeling demand for inventory optimization of slow-moving items

This paper presents the concept of inventory optimization and the role of demand distributions. Slow-moving item demand receives special emphasis. Simulations of several popular discrete distributions illustrate the difficulties of probability modeling with the quantity and quality of demand history typically available. Results of experiments with a state-of-the-art probability modeling tool (EXpertFit ^TM) highlight the practical difficulties of data-fitting. Finally, inventory optimization over a simulated data set with the “wrong” assumed demand distribution suggests a business case for accurately identifying demand distributions