A Predictive Decision-Support Framework Using Machine Learning Algorithms to Mitigate Supply Chain Risks and Optimize On-Time Delivery of Gas Turbine Jet Engines
Open Access DepositedThis praxis explores the critical challenge of achieving on-time delivery (OTD) for precision components in gas turbine jet engines, which is essential for fulfilling Department of Defense contracts. The focus is on a prominent aerospace engine manufacturer recognized for its advanced technologies and significant market presence in both commercial and defense sectors. In 2023, the company generated approximately $26 billion in revenue, reflecting double-digit growth driven by strong demand across its portfolio. The manufacturer contends with substantial supply chain disruptions, including labor shortages, geopolitical tensions, and impacts from the COVID-19 pandemic. To address these challenges, a predictive decision-support tool utilizing machine learning algorithms such as Random Forest and Gradient Boosting was developed. This tool integrates critical data on supplier performance and part complexity, enhancing the ability to forecast potential delays and allocate resources effectively. The predictive model supports proactive supply chain risk management, thereby optimizing OTD performance. The findings reveal that supplier ratings and part complexity significantly influence OTD, underscoring the practical value of predictive analytics in complex manufacturing settings. This decision-support framework not only improves supply chain resilience but also offers a scalable solution that can be adapted to other precision manufacturing industries dependent on timely deliveries.
- All rights reserved
Notice to Authors
If you are the author of this work and you have any questions about the information on this page, please use the Contact form to get in touch with us.
| Thumbnail | Title | Date Uploaded | Visibility | Actions |
|---|---|---|---|---|
|
|
PeeplesJr_gwu_0075A_17130.pdf | 2025-04-11 | Open Access |
|