．單位首頁
．系所簡介
．系主任
．強力師資
．研究所
．課程概況
．各類學程
．期刊論文
．招生資訊
．演講專區
．榮譽榜
．系學會
．系友天地
．就業訊息
96年3月16日(五) 2:00 ~3:00 P.M.
演講者姓名： Dr. Philip L.H. Yu
演講者服務單位： Department of Statistics and Actuarial Science, University of Hong Kong
演講題目：Independent component analysis and its application in finance摘要：Independent component analysis (ICA) is a data mining technique which aims to express a set of random variables as linear combinations of statistically independent latent components. Because of its ability to model multivariate non-Gaussian data such as financial time series data, financial applications of ICA began to appear in recent years. This talk will present some recent work on the extension of ICA in modeling multivariate time series, including multivariate volatility modeling using ICA with each independent component being modeled by a separate generalized autoregressive heteroskedastic (GARCH) process and term structure modeling using ICA. Some work on validating ICA modeling will be discussed.
