Optimising forecasting models for inventory planning

Abstract

Inaccurate forecasts can be costly for company operations, in terms of stockouts and lost sales, or over-stocking, while not meeting service level targets.The forecasting literature, often disjoint from the needs of the forecast users, has focused on providing optimal models in terms of likelihood and various accuracy metrics. However, there is evidence that this does not always lead to better inventory performance, as often the translation between forecast errors and inventory results is not linear. In this study, we consider an approach to parametrising forecasting models by directly considering appropriate inventory metrics and the current inventory policy. We propose a way to combine the competing multiple inventory objectives, i.e. meeting demand, while eliminating excessive stock, and use the resulting cost function to identify inventory optimal parameters for forecasting models. We evaluate the proposed parametrisation against established alternatives and demonstrate its performance on real data. Furthermore, we explore the connection between forecast accuracy and inventory performance and discuss the extent to which the former is an appropriate proxy of the latter.

Joint Effect of Forecasting and Lot-Sizing Method on Cost Minimization Objective of a Manufacturer: A Case Study

“…In recent empirical research, Ali & Miller, 2017 also found that one of the most problematic and yet unresolved areas of ERP implementation is identifying and agreeing on the industry-standard implementation model. Moreover, as argued by Kourentzes et al (2020), the inventory gains originate a more difficult optimization problem. In the context of MRP, Li & Disney (2017) also found that MRP systems are not always fully implemented, generate some consistency issues, and are unable to generate accurate data.…”

“…Inventories are considered to be one of the key assets of an organization, the size of inventory can be determined through different forecasting techniques (Silver, Pyke & Thomas, 2016). Inaccurate forecasts turn out to be expensive for organization operations, in terms of overstocking or stock-outs and lost sales, while the desired service level is not being met (Kourentzes, Trapero & Barrow, 2020). Inventory planning mainly focuses on when to order and how much to order, the lot sizes.…”

Forecasting for social good

“…This is because the translation between forecast errors and social good metrics might not be linear. This is a well-known issue in forecasting for inventory control (Kourentzes, Trapero, & Barrow, 2020;Syntetos et al, 2009). Another example would be identifying appropriate loss functions for social good so as to estimate the parameters.…”

Development of a hybrid framework for inventory leanness in Technical Services Organizations

“…Most of the less recent research on inventory management focuses on traditional inventory control models. Researchers of that era have either assessed conventional inventory control models under specific conditions or combined additional deliberations into established models [ 18 ]. The basic (Q, r) inventory control model was introduced by Harris [ 5 ], which allowed an organization to place orders of size (Q) whenever its inventory position reaches a re-order point (r).…”

“…For example, researchers have considered certain additional factors, like transportation [ 19 ], buyer/seller relationships [ 20 ], quality considerations, short lead times and emergency conditions, etc. [ 18 ]. and have further evaluated the approach under particular demand and lead-time distributions [ 21 ].…”