A Design of a Mass Customization Production System Based on Data-Driven Optimization

2023 Fiscal Year Final Research Report

• Project/Area Number: 19K15243
• Research Category: Grant-in-Aid for Early-Career Scientists
• Allocation Type: Multi-year Fund
• Review Section: Basic Section 25010:Social systems engineering-related
• Research Institution: Waseda University
• Principal Investigator: Ohmori Shunichi 早稲田大学, 理工学術院, 准教授 (30649348)
• Project Period (FY): 2019-04-01 – 2024-03-31
• Keywords: サプライチェーンマネジメント / 分布的ロバスト最適化

Outline of Final Research Achievements

To respond to the diversification of customer needs in recent years, many manufacturing industries face the critical challenge of transforming to "mass customization," which combines the economies of scale with personalized responses to individual consumer preferences. To meet these seemingly contradictory demands, it is necessary to make rapid and integrated decisions involving (1) creating demand scenarios based on market and sales data and (2) designing a supply chain robust against demand uncertainties. However, this is not easy due to the need for inter-organizational collaboration.

This study aims to develop a scientific method for integrated decision-making on (1) and (2) by leveraging market, sales, and production data across organizational boundaries. Specifically, we propose a new methodology using a model called "data-driven optimization" and demonstrate its effectiveness.

Free Research Field

サプライチェーンマネジメント

Academic Significance and Societal Importance of the Research Achievements

迅速な意思決定が求められる昨今において、市場データから多様な顧客ニーズをいち早く理解し、顧客・製品特性に合わせた最適なサプライチェーン設計を行うことは、マス・カスタマイゼーションの実現に向けて強力な意思決定支援ツールとなる。また、上記の目的実現のために、ノンパラメトリック推定と分布的ロバスト最適化を融合した新しい先進的な手法を適用した。SC設計のみならず、大規模データを活用した予測・最適化を統合した意思決定全般への展開が期待できる。また、実企業との共同研究を通じて実データを用いた検証を行った。実証的に研究を評価できたことは社会実装を進める上でも意義が大きい。