Forecasting intermittent demand by fuzzy support vector machines

Intermittent demand appears at random, with many time periods having no demand,which is probably the biggest challenge in the repair and overhaul industry. Exponential smoothing is used when dealing with such kind of demand. Based on it, more improved methods have been studied such as Croston method. This paper proposes a novel method to forecast the intermittent parts demand based on fuzzy support vector machines (FSVM) in regression. Details on data clustering, performance criteria design, kernel function selection are presented and an experimental result is given to show the method's validity.