Data-Driven Lot Sizing With Random Yield
Abstract
Motivated by yield uncertainty in semiconductor manufacturing, we explore a data-driven lot sizing problem under random yield. Our focus is on the case where the random yield rate of the process depends on a number of features that can be observed before the lot sizing decision is made. We develop and compare the performance of different estimation and optimization approaches for this problem. We calibrate and test the methods on a publicly available data set for feature-dependent semiconductor yield data which presents challenges that are typical in prescriptive analytics in operations: a large number of features and relatively few observations.
Authors: Fikri Karaesmen, Koç University (joint work with Bijan Bibak)
About Firki Karaesmen
Fikri Karaesmen is a Professor of Industrial Engineering at Koç University currently visiting Imperial College. He received his BS degree from METU (Ankara, Turkey) and MS and PhD degrees from Northeastern University (Boston, MA, USA). His main research interests are in stochastic modelling with applications to production, inventory, and service systems.
***This seminar will take place in person in room T09-67. Alternatively, click here to join the seminar online.
Meeting ID: 366 381 125 159
Passcode: aL9Py96Y
Information
- Type
- Research Seminar
- Programme
- Logistics & Information Systems
- Date
- Mon. 7 Apr. 2025
- Time
- 11:00 - 12:30
- Location
- T09-67 or Teams
