UVF3B403: Data mining - Fall 2017/2018


Back
MSC 2A DS Automne
EDF03B403
  Presentation
 
Knowledge extraction uses data, accumulated occasionally or over a period of time, to produce decision elements which answer either a specific need such as identification or a specific population (housewives under 50 for example), or a more general need like population segmentation (identifying the different uses of a service such as a web site, for example).

A combination of data analaysis, learning and data bases, this domain has expanded greatly in recent years thanks to the increase in computer calculation power, making it possible to process larger and larger amounts of data rapidly. It is now possible to process domains producing large amounts of data such as the client base of a supermarket company or bio-computing genetic data.

This unit presents the various approaches and methods which form the theoretical basis of decisional computing.

The type of methods presented will depend on the processing objective. Several cases are possible and each one is covered in a specific module:
- One wishes to determine the "logical rules" generating the creation of data (the great majority of people who buy beer also buy chips, for example). Module: 'Knowledge extraction"

One wishes to break data down into "homogenous" groups (notion of "homogeneity" remains to be defined) without a priori knowledge of the groups in question. Module: "Classification"

- One wishes to predict which classes data will be assigned to (for example, a banker wishes to separate customers into two groups, those eligile for a loan and those not eligible). Module: "Statistic learning"

About 25% of the unit is set aside for practical learning where students get to grips with the different analytical methods.

After following this unit, students can use a variety of methods and tools to solve most problems relating to Data Analysis.
 
Access conditions  : - ISA option (UV)
- open to other options
- no conditions
 
Location  : BREST
Coordinator  : Philippe LENCA
Co-Coordinator  : Sorin MOGA
Dernière màj le 25-APR-17 par CURSUS
  Modules
 
Code Intitulé
Title
Responsable
Coordinator
Co-resp. Etat
State
Date màj
Last update
F3B403A Knowledge extraction from data P.Lenca   Incomplète 25-04-17

IMT Atlantique
Campus de Brest
Technopôle Brest-Iroise
CS 83818
29238 Brest Cedex 3
France

Tél  +33 (0)2 29 00 11 11
Fax +33 (0)2 29 00 10 00
Lexians