2019 INFORMS Annual Meeting

Description

Forecasting problem is one of the crucial considerations in the application domain of epidemiology, especially while analyzing the influenza data with internet search queries. Individual learning approaches, such as time series model, e.g., ARIMA, and regression methods, e.g. PCR, LASSO and Elastic-net play essential roles in solving forecasting problems. Since each individual learning method has its own advantages and limitations, there has been an increasing interest in ensemble learning approaches, such as data fusion and model assimilation, that can achieve better forecasting performance, typically by the Bayesian model averaging. In this work, we focused on the statistical properties and theoretical issues of Bayesian model averaging around the forecasting problem. Additionally, we conducted a comparative study among various forecasting methods using the influenza-like-illness in general outpatient clinics (ILI-GOPC) data in the U.S. and Hong Kong.

Period	20 Oct 2019
Event type	Conference
Location	Seattle, United States, WashingtonShow on map
Degree of Recognition	International