[Forum SIS] Bocconi TWO-DAY Seminar Bozdogan - September 14th/15th

[Marco Bonetti]

The DEC Department is pleased to invite You to the seminar:

"A new modern approach to statistical data mining using information  
complexity and the genetic algorithm"

held by:

Hamparsum Bozdogan
(The University of Tennessee, USA)

Monday 14th September 2009 (h. 2.30 pm) Room N31
Tuesday 15th September 2009 (h. 9.30 am) Room N30
Piazza Sraffa 13 - 20136 Milano

Abstract:

In the information age we live in today, with increasingly  
sophisticated technology for gathering and storing data, many  
organizations and businesses collect massive amounts of data at  
accelerated rates and in ever-increasing detail. Massive data sets  
pose a great challenge to many cross-disciplinary fields. Such data  
sets have large number of dimensions and often have huge numbers of  
observations. They are categorical, discrete, quantitative, and often  
are mixed-data types. This high dimensionality and different data  
types and structures have now outstripped the capability of  
traditional statistical methods, data analysis, graphical and data  
visualization tools.
Researchers, practitioners, and Ph.D. students at all levels need new  
and modern highly clever model selection tools as a key tool  embedded  
into fast and efficient algorithms to reduce dimensionality and to  
choose best subset of variables in regression, classification, and  
cluster analysis to mention a few.
To address these challenges, this workshop seminar will present a new  
statistical model selection tools to analyze potentially massive data  
sets with the goal of identifying a parsimonious model structure to  
fit to the data.

To this end, during the first day of the seminar, we will present:
• A Short Overview of Data Mining & Statistical Methodology During the  
Last Five Years
• The General Theory and Applications of a New Information Complexity  
(ICOMP) Class Criteria for Model Selection
• Simultaneous Model Selection in Multivariate Mixture Model Cluster  
Analysis Using Information Complexity and the Genetic Algorithm: M3

During the second day of the seminar we will present:
• New Advances in Regression Model Selection Using Information  
Complexity and the Genetic Algorithm
• Lab Applications of Model Selection

===

You are all invited.
Sincerely,

Marco Bonetti


-------------- next part --------------
A non-text attachment was scrubbed...
Name: Locandina.pdf
Type: application/pdf
Size: 35741 bytes
Desc: not available
URL: <http://www.stat.unipg.it/pipermail/sis/attachments/20090908/2a329cc8/attachment-0001.pdf>
-------------- next part --------------


---
Marco Bonetti
Department of Decision Sciences
Bocconi University
Via Guglielmo Roentgen 1
20136 Milan, Italy
Tel +39 02 58365670
Fax +39 02 58365634