Applications of Machine Learning in the Supply Chain
An overview of research being conducted by Dr. Sebastian Pokutta, Associate Professor at the Stewart School of Industrial & Systems Engineering and Associate Director of the Center for Machine Learning @ GT, as part of the SCL Interdisciplinary Research Center seminar series.
SEMINAR DESCRIPTION
In this talk we will explore the possibilities of machine learning in supply chains and logistics. We will see that modern machine learning methods, often in a black box fashion, allow us to move from model-driven decision-making to data-driven decision-making. This results in high levels of flexibility and agility, which is of ever-increasing importance in fast-paced supply chain and logistics environments. We will lay out the foundation of this paradigm and look at specifics examples from the supply chain and logistics context.
ABOUT SEBASTIAN POKUTTA
Dr. Pokutta's research concentrates on combinatorial optimization and polyhedral combinatorics, and in particular focuses on cutting-plane methods and extended formulations. His industry research interests are in optimization and machine learning in the context of analytics with a focus on real-world applications, both in established industries as well as in emerging technologies. Application areas include but are not limited to supply chain management, finance, cyber-physical systems, and predictive analytics. To date, Dr. Pokutta has successfully deployed analytics methodology in 20+ real-world projects.
An overview of research being conducted by Dr. Sebastian Pokutta, Associate Professor at the Stewart School of Industrial & Systems Engineering and Associate Director of the Center for Machine Learning @ GT, as part of the SCL Interdisciplinary Research Center seminar series.
SEMINAR DESCRIPTION
In this talk we will explore the possibilities of machine learning in supply chains and logistics. We will see that modern machine learning methods, often in a black box fashion, allow us to move from model-driven decision-making to data-driven decision-making. This results in high levels of flexibility and agility, which is of ever-increasing importance in fast-paced supply chain and logistics environments. We will lay out the foundation of this paradigm and look at specifics examples from the supply chain and logistics context.
ABOUT SEBASTIAN POKUTTA
Dr. Pokutta’s research concentrates on combinatorial optimization and polyhedral combinatorics, and in particular focuses on cutting-plane methods and extended formulations. His industry research interests are in optimization and machine learning in the context of analytics with a focus on real-world applications, both in established industries as well as in emerging technologies. Application areas include but are not limited to supply chain management, finance, cyber-physical systems, and predictive analytics. To date, Dr. Pokutta has successfully deployed analytics methodology in 20+ real-world projects.
