Demand Planning for Resilient and Efficient Semiconductor Supply Chain

Interdisciplinary Areas: Data and Engineering Applications, Autonomous and Connected Systems, Smart City, Infrastructure, Transportation

Project Description

Semiconductor supply chain has faced various uncertainties, including volatile market dynamics, geopolitical tensions, pandemics, and extreme natural events. These present significant challenges to decision-making related to capacity planning, safety stock, and fulfilling customer orders. Addressing these challenges, this research aims to use advanced analytical techniques including AI/ML in the demand planning models of semiconductor supply chains to enhance resilience and efficiency.

Quantitative and qualitative data collection and analysis methods will be employed. In addition to traditional methods, advanced demand forecasting models using AI/ML techniques will be developed that are capable of accurately predicting and managing semiconductor demands. These models further help to develop strategies to manage risks and design a decision-support system to foster transparency in demand planning, making it more proactive and robust.
The research outcomes will benefit stakeholders in the semiconductor industry by enhancing operational resilience and capacity planning, improving cost efficiencies, and promoting long-term sustainability. Insights allow stakeholders to make informed, proactive decisions to handle potential supply chain disruptions and help to match supply and demand more effectively. The proposed data-driven basis for demand forecasts creates transparency that stimulates better coordination and facilitates collaborative decision-making, leading to a more integrated and responsive supply chain.

Start Date

Following announcement of Lillian Gilbreth Fellows

Postdoc Qualifications

- Doctoral Degree: Obtained a Ph.D. in a relevant field such as operations research, industrial engineering, supply chain management, logistics, systems engineering, transportation, or a related discipline.
- Research Experience: Prior research experience in demand forecasting and planning, supply chain management, semiconductor supply chain, system resilience, or related areas is highly valuable. This can include publishing papers in professional conferences or journals, participating in collaborative research projects, or conducting industry-driven research.
-Technical Skills: Having proficiency in various technical skills, including but not limited to:
+ Data Analysis and Modeling: Strong skills in statistical analysis, forecasting techniques, mathematical modeling, optimization, AI/ML, and simulation methods used in demand planning and supply chain research.
+ Programming and Software Tools: Familiarity with programming languages such as Python, R, or MATLAB for data manipulation, analysis, and building models. Additionally, knowledge of supply chain management software, such as SAP, Oracle, or demand planning tools, can be advantageous.
- Supply Chain Knowledge: Having a deep understanding of supply chain principles, including demand forecasting, inventory management, production planning, distribution network design, logistics, and risk management.
- Resilient Supply Chain Concepts: Having knowledge related to resilient supply chains, such as risk assessment and mitigation, supply chain disruptions, business continuity planning, and supply chain agility. Knowledge of methodologies like SCOR (Supply Chain Operations Reference) model and resilience frameworks is an advantage.
- Analytical and Problem-Solving Skills: Having strong analytical and problem-solving abilities to tackle complex supply chain challenges. This includes the ability to identify patterns, analyze data, and make informed decisions based on the findings.
- Communication and Collaboration: Excellent communication skills are crucial for presenting research findings, writing reports, collaborating with industry partners, and working effectively within research teams. You should also possess strong project management and teamwork skills.
- Industry Experience: While not mandatory, practical experience in the industry through internships, consulting projects, or collaborations would be desired as it can provide valuable insights into real-world semiconductor supply chain challenges.


Tho Le, PhD. Assistant Professor of Industrial Engineering Technology. School of Engineering Technology.

Young-Jun Son, PhD. James J. Solberg Head and Ransburg Professor. School of Industrial Engineering.

Short Bibliography

1. Dolgui, A., Tiwari, M. K., Sinjana, Y., Kumar, S. K., & Son, Y. J. (2018). Optimizing integrated inventory policy for perishable items in a multi-stage supply chain. International Journal of Production Research, 56(1-2), 902-925.
2. Meng, C., Hu, B., & Son, Y. J. (2014, December). Capacity reservation for a decentralized supply chain under resource competition: a game theoretic approach. In Proceedings of the Winter Simulation Conference 2014 (pp. 2036-2047). IEEE.
3. N. Celik, S. Nageshwaraniyer, and Y. Son, Impact of Information-Sharing in Hierarchical Decision-Making in Manufacturing Supply Chains, Journal of Intelligent Manufacturing, 23(4), 2012, 1083-1101.
4. Le, T. V., Stathopoulos, A., Van Woensel, T., & Ukkusuri, S. V. (2019). Supply, demand, operations, and management of crowd-shipping services: A review and empirical evidence. Transportation Research Part C: Emerging Technologies, 103, 83-103.
5. N. Koyuncu, S. Lee, K. Vasudevan, Y. Son, DDDAS-based Multi-fidelity Simulation Framework for Supply Chain Systems, IIE Transactions on Operations Engineering, 42(5), 2010, 325-341 (also introduced in IE magazine).