STAT 4001 數據挖掘及統計學習 Data Mining & Stat Learning

 

Course Code	STAT 4001 STAT4001			科目名稱		Data Mining & Stat Learning 數據挖掘及統計學習
教員	Professor LIN Zhixiang [官方介紹] [學術著作]			學　　分		3學分
課程性質	STAT選修 (Data Analytics Stream必修)			同科其他選擇
Workload	l   非PAPER類HOMEWORK l   MIDTERM l   FINAL EXAM								好重
									重
									平均
									輕	1
									極輕
評價教學內容	#1教好多Statistical Learning嘅algorithm, Tutorial全部都係R examples, Homework偏難且冇答案, 建議R底差嘅同學唔好讀
評價教員教學	#1講嘢好悶
CUSIS科目資料	Description： This course covers the principles of data mining, exploratory analysis and visualization, as well as predictive modeling for complex data sets. It introduces modern tools for regression and classification for high-dimensional or ultra-high dimensional data from the perspective of statistical decision theory and makes comparison to traditional methods. Students are exposed to statistical principles, computational issues, and hands-on data analysis on high noise, observational data.   Learning Outcome： Upon completion of the course, students should be able to  (1) use various statistical methods and techniques to summarize and present high-dimensional data;  (2) build predictive models for complex data sets;  (3) master the concepts of regularization, model selection, model averaging and ensemble learning; and  (4) write R code and use R packages to solve real-world problems.
其他資料	2021Sem1：學位 87|註冊 83|剩餘 4
同學推薦	高度推薦		推薦			有保留	1	極有保留

STAT 4002 多元技巧及其商業應用 Multivariate Tech W/ Bus App

Course Code	STAT 4002 STAT4002			科目名稱		Multivariate Tech W/ Bus App 多元技巧及其商業應用
教員	Professor LIN Zhixiang [官方介紹] [學術著作]			學　　分		3學分
課程性質	STAT/RMSC/QFRM/QFIN系選修			同科其他選擇
Workload	l   非PAPER類HOMEWORK l   MIDTERM l   FINAL EXAM								好重
									重
									平均
									輕	1
									極輕
評價教學內容	#1 Quite Interesting, 2019R2 有講Image PCA等比較現代而有趣嘅topic, 數學原理ok淺白但都要有basic matrix operation/probability and statistics概念
評價教員教學	#1 同一般stat course比起ok, 比較平舖直敘, 但assignment有趣而有用, tutorial多example which is good
CUSIS科目資料	Description： This course deals with multivariate statistical techniques and their applications in business. Topics are selected from multivariate normal distribution, analysis of means, profile analysis, MANOVA, partial correlation, multiple and canonical correlations, discriminant analysis, and principal components. The integrated use of these techniques in analysing business problems will be emphasized throughout the course.   Learning Outcome： (1) extend standard univariate techniques to their multivariate counterparts;  (2) describe and interpret correlation structures;  (3) perform and interpret multivariate techniques including principal component analysis, factor analysis, multivariate regression and discriminant analysis; and  (4) analyze real data by appropriate techniques and software.
其他資料	2019Sem1：學位 70|註冊 67|剩餘 3
同學推薦	高度推薦		推薦		1	有保留		極有保留