1. Data mining and real systems modeling
CERN December 2016
Genève
Data mining and real systems modeling
J. Chaskalovic
Institut Jean le Rond d’Alembert
University Pierre and Marie Curie

2. Agenda Modeling and real systems What’s Data Mining
Why Mine Data? Scientific Viewpoint
Why Mine Data? Commercial Viewpoint
Live Data Mining: a medical application

3. Modeling
&
real systems

4. Real systems modeling Too much independant !
Analytical
modeling
Experimental
research
Numerical
simulation
Understanding
Control
Forecasting

5. What’s Data Mining ?
Data mining is the knowledge discovery process in databases:
Efficient techniques which lead to the identification of interesting information or patterns from data usually in large databases.

6. Why Mine Data? Scientific Viewpoint
Data collected and stored at enormous speeds (GB/hour)
Remote sensors on a satellite.
Telescopes scanning the skies.
Scientific simulations generating terabytes of data.
Traditional techniques infeasible for raw data
Data mining may help scientists
In classifying and segmenting data.
In assumptions modelling (analytical modeling and experiments).

7. Why Mine Data? Commercial Viewpoint
Lots of data is being collected and warehoused
Web data, e-commerce.
Purchases at supermarkets or big department stores.
Bank / Credit Card.
Computers have become cheaper and more powerful
Competitive Pressure is Strong
Provide better, customized edge services (e.g. in Customer Relationship Management).

8. It’s coming from…

9. Customer Relationship Management
Interactivity devoted to develop
Clients Relationship
Optimization consumers’ relationships during the customer life cycle in several Marketing topics :
Recruitment (acquiring customers)
Loyalty (retaining good customers)
Sales (increasing the value of customers)
Better knowledge of Clients and Prospects :
It’s clear that the CRM we consider is based on the classical concepts which are the optimization of the consumers’relationship in the several topics as :
Recruitment
Loyalty,
Sales,
and, because the aim of the CRM is to develop an appropriate knowledge to each identified segment of the population to produce efficient strategies of Marketing and Communication, our view and contribution in this process is to add the dimension of the nature of the media which are used to communicate to the resulting identified clients or propects.
Which product
For which client
At which moment
From which media

10. Process of CRM & Data Mining
Step 1 : The Brief
Step 2 : Collect and Data Management
Step 3 : Data Analysis and Modeling
ANALYSIS
CLUSTERING
Step 4 : Segmentation of the Database
Step 5 : Optimization & Data campaign
ACTIONS
marketing &
communication
Feeding
Optimization
&
Learning process
Identifying
Deciding
Segmentating

11. Data Mining Principles
Supervised Data Mining : One or more target variables must be explained in terms of a set of predictor variables.
Segmentation by Decision Tree, Neural Networks, etc.
Non supervised Data Mining : No variable to be explained, all available variables are considered to create groups of individuals with homogeneous behavior.
Typology by Kohonen’s cards, Clustering, etc.

12. The Data Mining is a discovery process
Data Mining and not Data Analysis
The Data Mining is a discovery process
Data Scan : inventory of potential and explicative variables.
Data Management : collection, arrangement and presentation of the Data in the right way for mining.
Data Analysis :
Learning
Modeling
Forecasting
Ha taalih chel guilouï hou banouï kédé léfateah ète ha yeda chel hatsarkanim

13. Live Data Mining
Medical application

14. Thank you very much !