Thesis: M.B.A., Massachusetts Institute of Technology, Sloan School of Management, 2019, In conjunction with the Leaders for Global Operations Program at MIT / Thesis: S.M., Massachusetts Institute of Technology, Department of Mechanical Engineering, 2019, In conjunction with the Leaders for Global Operations Program at MIT / Cataloged from PDF version of thesis. / Includes bibliographical references (pages 87-88). / Historically, the Storage business unit of the Dell-EMC Infrastructure Solutions Group (ISG) has maintained large inventory buffers to deal with high demand uncertainty and minimize part shortages. High product configurability and complex product structures continue to present challenges to effectively managing component inventory. In addition, many supply and demand planning decisions are contextual rather than process driven, making it difficult to understand precisely how inventory level is influenced by its independent variables. The objective of this project is to develop a set of dynamic inventory policies to enable inventory reduction at ISG while maintaining or improving cycle service levels. Our approach is based on modeling the inventory behavior of the existing supply chain system, and generating inventory policies that more accurately reflect consumption within the system. Three parameterized inventory policies have been built and tested. / We modeled inventory, forecast and actual demand data, used demand classification techniques to selectively adjust policy recommendations for certain drives and validated policy performance by adjusting input parameters. Based on model training for three quarters from August, 2017 to May, 2018 and validation from May, 2018 to August, 2018 our final choice was an order-up-to policy developed by fitting empirical distributions to historical forecast errors and using those distributions to recommend safety stock levels. The policy was applied to 111 CFGs representing 2,758 part numbers. We used August, 2018 to November, 2018 as a test period and applied the policy to observe its performance. Results indicated a 96.40% service level and 36% mean inventory reduction as compared to the baseline, which had a 98.40% service level. The 3.60% loss of service represented 56 shortages. / Of those, we identified 31 that could be eliminated through simple policy refinement, leading to a revised service level of 98.55%. Overall, our results suggest that a mathematical inventory management approach can be used reliably to model the hard drive supply chain, recommend an inventory policy and realize significant inventory reduction opportunities without compromising service level. This thesis concludes by proposing important supply chain system design changes, where several issues at the root of ISG's inventory management challenges reside. / by Ephraim D. Machtinger. / M.B.A. / S.M. / M.B.A. Massachusetts Institute of Technology, Sloan School of Management / S.M. Massachusetts Institute of Technology, Department of Mechanical Engineering
Identifer | oai:union.ndltd.org:MIT/oai:dspace.mit.edu:1721.1/122571 |
Date | January 2019 |
Creators | Machtinger, Ephraim D. |
Contributors | Jung-Hoon Chun and Donald Kieffer., Sloan School of Management., Massachusetts Institute of Technology. Department of Mechanical Engineering., Leaders for Global Operations Program., Sloan School of Management, Massachusetts Institute of Technology. Department of Mechanical Engineering, Leaders for Global Operations Program |
Publisher | Massachusetts Institute of Technology |
Source Sets | M.I.T. Theses and Dissertation |
Language | English |
Detected Language | English |
Type | Thesis |
Format | 93 pages, application/pdf |
Rights | MIT theses are protected by copyright. They may be viewed, downloaded, or printed from this source but further reproduction or distribution in any format is prohibited without written permission., http://dspace.mit.edu/handle/1721.1/7582 |
Page generated in 0.0013 seconds