Cet espace sera supprimé le 31 janvier 2024 - Pour toutes questions, vous pouvez nous contacter sur la liste wikidocs-contact@univ-lorraine.fr

GIMAS9ADx

Data Analysis and Data Mining

 

ECTS Credits : 4 ECTS

Duration : 42 heures

Semester : S9

Person(s) in charge:

Sandie FERRIGNO, Associate Professor, Sandie.Ferrigno@mines-nancy.univ-lorraine.fr 

Keywords:

Data Analysis and Data Mining

Prerequisites:

Basic notions of SAS software, Stochastic Analysis and Statistics

Objective:

Data analysis methods and Data Mining

Program and contents:

Objectifs pédagogiques

In 70-80 years, the development of computers has led to the storage of information in the most classic form was the one that matched data tables, usually of large dimensions. In many areas (geology, meteorology, medicine, economics, marketing, quality control, pattern recognition ...), data analysis allowed to leverage this information to synthesize, to serve as the basis for a decision process, or more generally to understand somehow the nature of the phenomena underlying the data.  Since the 90s, systematic digitization of information that organizations, public or private, accumulate massive amounts of information stored in digital databases, amorphous and dynamic, data made of numbers, texts, images, sounds, etc. Data Mining is an "industrialization" of the data analysis to enable effective operation of the enterprise  information capital.

Contents - Program
The program focuses on the main data analysis methods and data mining :
PCA
Correspondence Analysis
Discriminant analysis
Classifications automatic
Discrimination and neuronal classification
Segmentation


Their implementation poses the user a number of issues , the main ones :
What kinds of problems can be treated?
Which method to choose?
What data choose?
What kind of results can we expect ?
What are its limits?
How to implement them?


A project carried out in teams, will allow each student, beyond learning techniques , to answer these questions and to learn to use a modern software environment for data analysis (SAS and JMP) .


References
G. Saporta, Probabilités, analyse des données et statistique, Technip.
M. Tenenhaus, Statistique, Méthodes pour décrire, expliquer et prévoir, Dunod.
L. Lebart, A. Morineau et M. Piron, Statistique exploratoire multidimensionnelle, Dunod.
S. Tufféry, Data Mining et statistique décisionnelle, Technip.

Abilities: 

Levels

Description and operational verbs

Know

 

Understand 

 

Apply

 

Analyze 

 

Summarise

 

Assess

 

Évaluations :

  • Written test

  • Continuous Control

  • Oral report
  • Project
  • Written report
  • Aucune étiquette