|
Lecturer(s)
|
-
Petr Pavel, doc. Ing. Ph.D.
|
|
Course content
|
Introduction to the DM. Methodologies DM. Methodology CRISP- content and structure particular phase. Using of the methodology CRISP. Business understanding Data understanding Data preparation Modeling Evaluation Usage results. Practical application.
|
|
Learning activities and teaching methods
|
|
Monologic (reading, lecture, briefing), Work with text (with textbook, with book), Methods of individual activities
|
|
Learning outcomes
|
Goal is introduce students with possibilities data miningu (DM).Attention paid to particular methodology with emphasis on methodology CRISP. There're show up individual phase those methodology on concrete example with usage tools SPSS and Clementine. Detailed is disassembly problems single methods for creation models.
Students will understand basic points of applied fields of data mining projects and will be able to operate individual project phases using the CRISP-DM methodology. In addition, they will know the base of the appropriate methods for a model creation and understand their right application in practice.
|
|
Prerequisites
|
unspecified
|
|
Assessment methods and criteria
|
Oral examination, Work-related product analysis, Creative work analysis
Requirements to inclusion: work up engaged exercise on exercising and seminar with fruitfulness mine. 60%, transfer semestral work according to setting. Requirements to examination (inclusive forms examination): verbal State one's case (rout) of the semestral work. Resulting evaluation is given to ratio 40% exercising and seminars, 50% case for the defense final work and reaction to questions examiner, 10% rout semestral work.
|
|
Recommended literature
|
-
BERRY, M. - LINOFF G. Data Mining Techniques - For Marketing, Sales, and Customer Relationship Management. Indianapolis, John Wiley & Sons, 2004, 643 s.. 2004.
-
GUIDICI P. Applied Data Mining - Statistical Methods for Business and Industry. Guildford, John Wiley & Sons, 2003, 364 s.. 2003.
-
PYLE, D. Data Preparation for Data Mining. San Diego, Academic Press, 1999, 540 s.. San Diego, 1999.
|