Mass Customization and Forecasting Options' Penetration Rates Problem

• 成果类型: Article
• 署名作者: Fattahi, Ali; Dasu, Sriram; Ahmadi, Reza
• 署名单位: University of California System; University of California Los Angeles; University of Southern California
• 刊物名称: OPERATIONS RESEARCH
• ISSN/ISSBN: 0030-364X
• DOI: 10.1287/opre.2018.1795
• 发表日期: 2019
• 页码: 1120-1134
• 关键词: product; configuration; optimization; systems

摘要

Auto manufacturers produce a very large number of feasible configurations that make it impossible to forecast the demand of individual configurations. What the companies do forecast is the penetration rate of each option, which is the percentage of cars that include that option. The current forecasting approach ignores rules for selecting options, and as a result, forecast penetration rates are frequently infeasible, which results in excess inventories, shortages, and customer dissatisfaction. The problem of determining the feasibility of the forecast penetration rates and finding the best feasible penetration rates in the case of infeasibility is NP hard. This problem is formulated as finding a point in the convex cone of the feasible configurations that has the minimum Euclidean distance to the forecast penetration rates. We present an approach, similar to a variant of the Frank-Wolfe method, that sequentially constructs the feasible region and stops when it finds the best feasible penetration rates. We analyze the theoretical properties of our approach and provide insights on its convergence rate. We also show the effectiveness of our approach on a set of real instances from a large auto manufacturer.