SVR-based method forecasting intermittent demand for service parts inventories

Intermittent Demand forecasting is one of the most crucial issues of service parts inventory management, which forms the basis for the planning of inventory levels and is probably the biggest challenge in the repair and overhaul industry. Generally, intermittent demand appears at random, with many time periods having no demand. In practice, exponential smoothing is often used when dealing with such kind of demand. Based on exponential smoothing method, more improved methods have been studied such as Croston method. This paper proposes a novel method to forecast the intermittent parts demand based on support vector regression (SVR). Details on data clustering, performance criteria design, kernel function selection are presented and an experimental result is given to show the method's validity.