Integrated multi-period dynamic inventory classification and control

doi:10.1016/j.ijpe.2017.04.010

Return

Integrated multi-period dynamic inventory classification and control

2017-07-01

PRE

DOI：10.1016/j.ijpe.2017.04.010

Original

Original request for help

Save

Abstract

En 中文

This paper investigates the dynamic integration and optimization of inventory classification and inventory control decisions to maximize the net present value (NPV) of profit over a planning horizon. A mixed-integer linear programming model is developed by explicitly accounting for various real-world complexities, such as nonstationary demand, arbitrary review period, and limited inventory budget. We apply the model to a 900-SKU experiment and observe an average 7.5% improvement in profit over the traditional ABC approach. A real world application for a cheese manufacturer provides a nearly 3% improvement in company's profit with a 13% reduction in inventory capital compared to its current eight-class multi-criteria inventory classification scheme. Comprehensive computational experiments are performed to examine the individual and interactive effects of various parameters on the inventory performance. Results show that it is critical for a company to manage its inventory both dynamically in the face of nonstationary demand and holistically by integrating SKU classification and policy setting. Our work provides a practical decision-support tool that simultaneously optimizes multi-period inventory classification and control decisions under nonstationary demand. It contributes to the inventory management literature by bridging two distinct streams of inventory research, inventory classification and inventory optimization, within a practical inventory modeling framework. Our study also offers several managerial implications for manufacturers and distributors managing finished goods inventory.

Keywords:

Inventory classification

Profit maximization

Inventory management

Nonstationary demand

Mixed-integer programming

AI Summary

Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.