|When:||Wednesday May 22, 2013 Noon - 2 PM|
|Place:||The Penn Club, 30 West 44th Street, New York, NY|
|Reservations:|| Call John Waldes at (212) 362-0302 or email him.
|Cost:||$55 for non-members, $45 for
$5 surcharge for walk-in without reservation.
First-time Attendees : $35 membership + $20 lunch
|Topic:||Comparative Review of Classification Trees|
|Abstract:||This presentation describes the steps involved in tree methodology for classification purposes. A modeler using the most popular technique, logistic regression, must impute the missing values first and the proceed with a variable selection tool.
Classification refers to identifying probable responders to a marketing campaign, fraudsters in business practices, disease in clinical analysis for instance. In the world of large observational data sets, they typically contain missing values and models must be searched.
In this presentation, we will compare the two approaches by way of an example and, if time permits, we will also describe further developments in the area of tree modeling, such as gradient boosting.
Breiman's et al 1984 monograph is the basis for CART, one of the most important Classification And Regression Tree methods. Other tree methods and corresponding software include C4.5 (Quinlan, 1993), Mathsoft's S+ (Clark and Pregibon, 1992), Chaid (Kass). See Steinberg (1993) and references therein.
Independent Statistical Research Consultant
Leonardo Auslender is a statistician (and economist) with more than 25 years of business experience and SAS expertise. His area of expertise is in the area of Giga-Data Analysis and Methods, and has written papers and given lectures on Variable Selection, Missing Value Imputation, Tree Regression, Support Vector Machines, Market-Basket Analysis, Data Base Marketing, CRM, GDP and (Relative Price) Inflation studies, Expectation Formations, Productivity and Technology effects in the economy. He was a lecturer of Finance and Macroeconomics at Rutgers University.
He presented two seminars on Market Basket Analysis in New York City (Informs and Amcis), a two-day seminar at the NYC Direct Marketing Association on Variable and Feature Selection in November, 2004, on Colinearity and Variable Selection at the December 2005 SCMA meeting in Auburn, Alabama, on Modeling issues at the SAS M2007 and M2008 Data Mining Conferences and at the Informs in NYC.