Abstract

In this talk, we will argue that the underlying “physics” of the system being modeled should play a significant role in the analysis of data sets, even those emanating from the world of "big data”. In particular, we will discuss how the extensive queueing limit theorems lend insight into what time scales and features of the incoming arrivals principally affect system performance. This suggests that statistical analysis of such arrivals should therefore focus on those time scales and on accurately measuring those statistical parameters. To leverage this perspective, we develop various statistical tools to fit arrivals data in a way that can enhance operational decision making. 

Zeyu Zheng is currently a Ph.D. student in the Department of Management Science and Engineering at Stanford University, under the supervision of Professor Peter W. Glynn. He obtained his Ph.D. minor in Statistics and M.A. in Economics from Stanford University, and B.S. in Mathematics from Peking University. His research interests lie at the interface of operations research, data sciences, and finance.