Order Quantity Distributions in Make-to-Order Manufacturing: At What Level of Aggregation Do They Respect Standard Assumptions?

Abstract

Abstract. This paper presents both an analytical and a numerical investigation into the order quantities received by a company in the form of customer orders. A discussion of assumptions regarding the behavior of demand in the form of customer orders from various perspectives within manufacturing planning and control with a special emphasis on the make-to-order environment is presented. A methodological framework for analyzing the behavior of orders and investigate the validity of the assumptions is given. Furthermore, an analytical approach to identify the horizon needed for aggregating orders to achieve a stable demand is developed and tested on data from a real case. Keywords:Poison process, aggregate demand, order sizes, planning horizon. IntroductionCompanies are in the business of satisfying customer demands in the form of customer orders. This paper focuses on the operational characteristics of ordering behavior in the form of demand and discusses the underlying assumptions within a number of fields. These characteristics include volume per planning period (demand rate -often disaggregated to several time horizons and described as a distribution of stochastic variables), accumulation of demand over the planning period, the number of orders per product per planning period and the standard order quantities for each product. The characteristics of the make-to-order manufacturing are depicted by Hendry and Kingsman [9] and Marucheck and McClelland [10]:• resources are multi-task machinery and flexible workforce -a large number of possible end items within a product line, • product lead time is vital for customer satisfaction and agreed with customer before production commences,

A Design of Experiments Approach to Investigating the Sensitivity of the Re-order Point Method

“…Fliedner (2001)). This finds support in Nielsen et al (2010) and methods for calculating adequate aggregation horizons to achieve a satisfactory distribution of demand can be found in Eriksen and Nielsen (2011). D d @1:C d @1:σ LT @0 is likewise a significant second order interaction with a negative contribution in all four models.…”

“…Previous work by e.g. Eriksen and Nielsen (2011) and Nielsen et al 2010 indicates that demand rates are in fact neither normal nor symmetrical distributed in practice. This underlines that this topic deserves further investigations.…”

Order Quantity Distributions: Estimating an Adequate Aggregation Horizon

“…customer orders that can be aggregated is challenged in this research through an investigation of actual behavior and modelling of what to do when customer orders are in fact not i.i.d. This paper expands on the work reported in [3] through adding a framework, extending the complexity of the model, elaborating on the current state and adding more numerical examples. This paper focuses on customer order quantity distributions, analyses their behavior and investigates the consequence of transforming these into demand rates that are used for planning purposes.…”