IDA

1
IDA Intelligent Data Analysis

• Transfer Team

2
We, The Transfer Team.
??
??
??
???
3
Outline

• Why IDA?
• The definition of IDA
• Knowledge and rules
• Tools for IDA
• Evaluation of IDA results
• Reference

4
Why IDA - Interest and Excitement

• Decision making is asking for information and
  knowledge.
• Data processing can offer this stuff.
• Multidimensionality of problems is looking for
  methods for adequate and deep data processing and
  analysis.

5
The definition of IDA

• IDA is an interdisciplinary study concerned with
  the effective analysis of data
• IDA is used for extracting useful information
  from large quantities of online data extracting
  desirable knowledge or interesting patterns from
  existing databases
• IDA is a way of data analysis based on artificial
  intelligence, on methods enabling to find out
  information and knowledge for a particular data
  domain.

6
Also known as
7
IDA gives Knowledge
8
Knowledge is

• The distillation of information that has been
  collected, classified, organized, integrated,
  abstracted and value-added
• At a level of abstraction higher than the data,
  and information on which it is based and can be
  used to deduce new information and new knowledge
• Usually in the context of human expertise used in
  solving problem.

9
Knowledge in a domain can be expressed as a
number of rules
10
Rule is

• A formal way of specifying a recommendation,
  directive, or strategy, expressed as IF premise
  THEN conclusion or IF condition THEN action

11
How to discover rules hidden in the data?
12
Tools for IDA - See 5

• The program for analyzing data and generating
  classifiers in the form of decision trees and or
  rule sets.
• IF (attribute1 is less-equal-greater-then v1 and
  attributen is less-equal-greater-then vn) THEN
  (class is equal ci)  

13
Tools for IDA - Cubist

• Analyzes data and generates rule-based piecewise
  linear models collections of rules, each with
  an associated linear expression for computing a
  target value.
• IF (attribute1 is less-equal-greater-then v1 and
  attributen is less-equal-greater-then vn) THEN
  (class is a function-linear-regression of
  attributes)

14
Tools for IDA - ILLM

• The tool constructs classification models in the
  form of rules which represent knowledge about
  relations hidden in data.
• IF (attribute1 is less-equal-greater-then v1 and
  attributen is less-equal-greater-then vn) THEN
  (class is equal ci)

15
Tools for IDA - Magnum Opus

• Finds association rules providing competitive
  advantage by revealing underlying interactions
  between factors within the data.
• IF (attributei is less-equal-greater-then vi and
  attributen is  less-equal-greater-then vn) THEN
  (attributej is less-equal-greater-then vj )
• or
• IF (itemi itemk itemn) THEN itemj

16
Evaluation of IDA results

• Absolute relative accuracy
• Sensitivity specificity
• False positive false negative
• Error rate
• Reliability of rules
• Etc

17
Reference

• http//en.wikipedia.org/wiki/Data_mining
• http//www.umin.ac.jp/supercourse/lecture/lec5131/
  index.htm
• http//www.rulequest.com/

18
Thanks

• Transfer Team