Statistics 6704 – Spring, 2008
Data Mining Methodology II
 

Department of Statistics
University of Central Florida
 

·         Announcement: 

• In correspondence to the Fourth Annual Business Intelligence Symposium in Orlando, FL on April 11, 2008, the Data Mining program at the University of Central Florida (UCF) is announcing a data mining competition on marketing response analysis in collaboration with BlueCross BlueShields of Florida (BCBSFL). Here is the website: http://dms.stat.ucf.edu/competition08/home.htm
• Please register for the Fourth Annual Business Intelligence Symposium at http://dms.stat.ucf.edu/competition08/symposium2008.htm.
• Several other ongoing data mining contests that you might be interested:
  • Second Annual Data Mining Shootout sponsored by SAS D2008:    http://www.sas.com/events/dmconf/contestform.html  
  • DMC2008:     http://www.data-mining-cup.com/2008/
  • UCSD Data Mining Contest 2008:    http://mill.ucsd.edu/index.php?page=Datasets&subpage=Overview
     

·         Description of the Course:     Data mining is the process of exploration and analysis, by automatic or semiautomatic means, of large quantities of observational data in order to discover meaningful patterns and models to the data owner. By applying data mining techniques, data miners can fully exploit data patterns and behavior, and gain a greater understanding of the inside of the data. The goal of data mining application in business is to produce new knowledge that decision-makers can act upon. It does this by using sophisticated techniques such as logistic regression and decision trees to build a model of the real world based on data collected from a variety of sources including corporate transactions, customer histories and demographics, and from external sources such as credit bureaus. This model produces knowledge that can be used to support decision-making and to predict new business opportunities. This course will cover data mining techniques such as association rules, statistical parametric/nonparametric regression, decision trees & their extensions (bagging, boosting, and RF), GAM, MARS, projection pursuit, neural networks, SVM, and etc.
 

·         Statistical Computing:  
 

o    Both SAS 9.1 with Enterprise Miner 5.2 and R will be used to do the statistical computing involved in this class.. In order to reinstall the newest version of SAS and SAS Enterprise Miner on your laptop computer, please contact the data mining lab, which is located at Room 350, MAP Building. Before you go, please check their time schedule. 

o    R can be downloaded free from from the website of CRAN: http://cran.r-project.org/ . Clink here to Download R-2.6.1-win32.exe or  http://cran.r-project.org/bin/windows/base/R-2.6.1-win32.exe.  
 

·         Syllabus and the Grading Policy:

Range	94+	93-90	89-87	86-83	82-80	79-77	76-73	72-70	69-67	66-63	62-60	59-0
Grade	A	A-	B+	B	B-	C+	C	C-	D+	D	D-	F

• Class Notes: The Acrobat Reader is needed in order to view pdf files appropriately.

Chapter	Notes	Data Sets	SAS Programs	R Programs
1	Introduction - Overview of Data Mining Techniques
2	Association Rules	BNKSERV.SD2		R-2.R
3	An Introduction to R
4	Simple Linear Regression Models		SAS-4-1.sas	R-4-1.R
5	Multiple Linear Regression Models and GLM (1, 2, 3)	bb87.dat	SAS-5-1.sas	R-5.R
6	Parametric Nonlinear Regression(1,2)		SAS-6.sas	R-6.R
7	KNN, Kernel Smoothing and Regression		SAS-7.sas	R-7.R
8	Regression / Smoothing Splines		SAS-8.sas	R-8.R
9	Generalized Additive Models (GAM)		SAS-9.sas	R-9.R
10	Tree-Based Methods			R-10.R
11	Boosting			R-11.R
12	Bagging and Ransom Forests			R-12.R
12-2	Bagging and Boosting in SAS EM	pen.sas7bdat
13	Multivariate Adaptive Regression Splines (MARS)			R-13.R
14	Projection Pursuit Regression (PPR)			R-14.R
15	Neural Networks I - Introduction
16	Neural Networks II (1,2,3,4)	EXPCAR.SD2
17	Neural Networks III - SAS EM Examples	hmeq.sas7bdat		R-17.R
18	Support Vector Machine (SVM), SVM-R		SAS-18.sas

 

·         Homework assignments and Class Handouts:

To ensure the homework assignment completed on time, the following grading policy will be applied. Any late homework assignment submitted within two days after the due day will be counted as 50%.  Submissions in more than two days after the due day assignment for any reason will not be graded and counted as 0 point.

• Reading Articles and Materials
   
• Association Rules
• Rakesh Agrawal and Ramakrishnan Srikant. Fast Algorithms for Mining Association Rules. In Proc. of the 20th Int'l Conference on Very Large Databases, Santiago, Chile, September 1994.
• R-Package: arules: M. Hahsler and B. Gr un and K. Hornik (2007). Introduction to arules – Mining Association Rules and Frequent Item Sets. 
• Linear Regression
• Larson, W.A. and McCleary, S.J. (1972).The Use of Partial Residual Plots in Regression Analysis. Technometrics, Vol. 14, No. 3. (Aug., 1972), pp. 781-790.
• Kernel Smoothing in SAS - PROC LOESS
• Fitting Curves and Surfaces Using SAS Software. from Information Systems Services at University of Leeds
• R. A. Cohen (1999), An Introduction to PROC LOESS for Local Regression, SAS Institute Inc.: Cary, North Carolina
• Altman, N.S. (1992). An Introduction to Kernel and Nearest-Neighbor Nonparametric Regression. The American Statistician, 46: 175-185.
• Regression/Smoothing Splines
• Wahba, G. " (Smoothing) Splines in Nonparametric Regression. " TR 1024, September 2000. In Encyclopedia of Environmetrics, A. El-Shaarawi and W. Piegorsch, Eds., Wiley, 4:2099-2112, 2001.
• GAM
• Hastie, T. and Tibshirani, R.(1986) Generalized Additive Models.Statistical Science, 1: 297-310.
• Bagging
• Breiman, L. (1996) Bagging predictors. Machine Learning, 24(2):123­140. PDF-link
• Boosting
• Freund, Y. and Schapire, R. E. (1999) A Short Introduction to Boosting. Journal of Japanese Society for Artificial Intelligence, 14 (5): 771-780.
• Culp, M., Johnson, K., and Michailides, G. (2006) ada: An R Package for Stochastic Boosting. Journal of Statistical Software. Vol. 17, Issue 2. Avialble from http://www.jstatsoft.org/v17/i02.

 

• Other Resources

• SAS -V9 Documentation is free on the web, both HTML and PDF http://support.sas.com/v9doc/, or within your software: HELP -> SAS Help and Documentation. 
• I also recommend you to have SAS System Viewer installed.
• Website for the textbook: The Elements of Statistical Learn
• R for SAS and SPSS Users (Word, PDF)
• Rattle: Gnome R Data Mining