Mendoza School of Business

Zifeng Zhao

Assistant Professor
IT, Analytics, and Operations
  358 Mendoza College of Business
  • Biography
  • Background
  • Publications
  • Grants

Zifeng Zhao is an Assistant Professor of Business Analytics at the Mendoza College of Business. His research focuses on solving business analytics problems via statistics and machine learning. His interests include developing copula-based statistical models for multivariate time series and multivariate longitudinal data, designing extreme value theory (EVT)-based models for financial risk monitoring, and building efficient staistical algorithms for change-point detection and large-scale forecasting. His research has been applied to areas like financial risk management, portfolio optimization, insurance risk classification and pricing, and web search traffic forecasting. Zhao has a PhD in Statistics and an MS degree in Machine Learning from the University of Wisconsin-Madison, and a BS degree in Financial Risk Management from the Chinese University of Hong Kong.

Ph D, University of Wisconsin - Madison
MS, University of Wisconsin - Madison
BS, Chinese University of Hong Kong

Areas of Expertise
Change Point Detection
Copula and Dependence
Extreme Value Theory
Time Series
Longitudinal Data Analysis

"Regression for copula-linked compound distributions with applications in modeling aggregate insurance claims", (With Peng Shi), Annals of Applied Statistics, 14, 2020

"Knowledge learning of insurance risks using dependence models", (With Shi Peng, Xiaoping Feng), INFORMS Journal on Computing - Accepted (awaiting publication)

"Dynamic bivariate Peak over Threshold model for joint tail risk dynamics of financial markets", Journal of Business & Economic Statistics - Accepted (awaiting publication)

"Modeling maxima with Autoregressive conditional Frechet model", (With Zhengjun Zhang, Rong Chen), Journal of Econometrics, 207, 2018

"Semi-parametric dynamic max-copula model for multivariate time series", (With Zhengjun Zhang), Journal of the Royal Statistical Society - Series B, 80, 2018

"Inference for multiple change-points in time series via likelihood ratio scan statistics", (With Chunyip Yau), Journal of the Royal Statistical Society - Series B, 78, 2016

"Regressor and disturbance have moments of all order, least squares estimator has none", (With Kenneth West), Statistics & Probability Letters, 115, 2016

Collaborative Research: Segmentation of Time Series via Self-normalization, NSF, $100,000

PHP Code Snippets Powered By :