黑料福利网

Topic 

Next Generation Workforce Scheduling with AI

Abstract

Optimizing schedules is one of the most challenging of optimization problems. To operate with the greatest efficiency, businesses must deploy the right number of workers to meet demand and minimize employee downtime on any given day. The COVID-19 pandemic brought about an unforeseen strain on day-to-day operations across many sectors, and as new regulations are imposed to grant flexibility of working from homes, traditional models based on Operations Research and Constraint Programming may no longer be used to generate rosters and schedules. Furthermore, disruptions such as employees not showing up for work at short notice or spikes in demand require that schedules be revised very quickly, yet most all-in-one optimization models take hours to deliver updated schedules.

In this talk we will discuss a combined staffing and scheduling problem that incorporates our concept of bounded flexibility and accounts for demand and supply uncertainty. This work was motivated by a real-world nurse rostering problem in a large hospital in Singapore. Our formulation distinguishes clearly between hard rules, which must be strictly adhered to, and flexible soft rules, which enable bounded flexibility to accommodate worker preferences (such as work from home arrangements). We will then discuss learning-based approaches based on Graph Neural Networks and Reinforcement Learning that allows schedules to be generated without an explicitly specified mathematical model. Finally, we discuss some prelim work leveraging on Large Language Models to directly perturb a Mixed-Integer Programming (MIP) formulation, resulting in a revised model capable of generating schedules that better reflect the decision-maker鈥檚 latent preferences.

About the speaker

Hoong Chuin Lau is Professor of Computer Science at the Singapore Management University, and currently on sabbatical leave at the Tohoku University, Japan.

His research interest is in planning, scheduling and reinforcement learning and their applications in logistics, transportation and healthcare domains. He was named the top 2% scientists in the world in a global study by Stanford University conducted since 2020. He has served on a number of editorial boards, including ACM Journal on Autonomous Transportation Systems, IEEE Transactions on Automation Science and Engineering, Journal of Heuristics, Journal of Scheduling, as well as on senior programme committees in AI conferences such as AAAI, IJCAI, ICAPS and AAMAS. In recognition of his achievements, contributions and service to academia and industry, he received the Outstanding Professor Award by the Industrial Engineering and Operations Management Society in 2021.

Your host

Yingqian Zhang, Associate Professor at the department of Industrial Engineering and Innovation Sciences of the 黑料福利网 will host Professor Hoong Chuin Lau.

Registration is required but free of charge.