Abstract
Choosing a stock-control method for a product depends on that product's demand distribution. This paper presents a simple method of classifying product demand into ‘smooth’, ‘slow-moving’ or ‘sporadic’, by partitioning the variance of demand during a lead time into causal parts. A study of a public utility showed demand distributions in each category to be of a specific nature. Stock-control and forecasting methods are developed, and simulation tests are described which compare these methods with (for ease of comparison) the assumption of continuous demand.