Knowledge Discovery in Databases


Published on

  • Be the first to comment

No Downloads
Total views
On SlideShare
From Embeds
Number of Embeds
Embeds 0
No embeds

No notes for slide

Knowledge Discovery in Databases

  1. 1. Data Mining: Concepts & Techniques
  2. 2. Motivation: Necessity is the Mother of Invention <ul><li>Data explosion problem </li></ul><ul><ul><li>Automated data collection tools and mature database technology lead to tremendous amounts of data stored in databases, data warehouses and other information repositories </li></ul></ul><ul><li>We are drowning in data, but starving for knowledge! </li></ul><ul><li>Solution: Data warehousing and data mining </li></ul><ul><ul><li>Data warehousing and on-line analytical processing </li></ul></ul><ul><ul><li>Extraction of interesting knowledge (rules, regularities, patterns, constraints) from data in large databases </li></ul></ul>
  3. 3. Evolution of Database Technology
  4. 6. What Is Data Mining? <ul><li>Data mining (knowledge discovery in databases): </li></ul><ul><ul><li>Extraction of interesting ( non-trivial, implicit, previously unknown and potentially useful ) information or patterns from data in large databases </li></ul></ul><ul><li>Alternative names and their “inside stories”: </li></ul><ul><ul><li>Data mining: a misnomer? </li></ul></ul><ul><ul><li>Knowledge discovery(mining) in databases (KDD), knowledge extraction, data/pattern analysis, data archeology, data dredging, information harvesting, business intelligence, etc. </li></ul></ul><ul><li>What is not data mining? </li></ul><ul><ul><li>(Deductive) query processing. </li></ul></ul><ul><ul><li>Expert systems or small ML/statistical programs </li></ul></ul>
  5. 7. Data Mining: A KDD Process <ul><ul><li>Data mining: the core of knowledge discovery process </li></ul></ul>
  6. 8. Steps of a KDD Process <ul><li>Learning the application domain: </li></ul><ul><ul><li>relevant prior knowledge and goals of application </li></ul></ul><ul><li>Creating a target data set: data selection </li></ul><ul><li>Data cleaning and preprocessing: (may take 60% of effort!) </li></ul><ul><li>Data reduction and transformation: </li></ul><ul><ul><li>Find useful features, dimensionality/variable reduction, invariant representation. </li></ul></ul><ul><li>Choosing functions of data mining </li></ul><ul><ul><li>summarization, classification, regression, association, clustering. </li></ul></ul><ul><li>Choosing the mining algorithm(s) </li></ul><ul><li>Data mining: search for patterns of interest </li></ul><ul><li>Pattern evaluation and knowledge presentation </li></ul><ul><ul><li>visualization, transformation, removing redundant patterns, etc. </li></ul></ul><ul><li>Use of discovered knowledge </li></ul>
  7. 9. <ul><li>The whole process of extraction of implicit, previously unknown and potentially useful knowledge from a large database </li></ul><ul><ul><li>It includes data selection , cleaning , enrichment , coding , data mining , and reporting </li></ul></ul><ul><ul><li>Data Mining is the key stage of Knowledge Discovery Process </li></ul></ul><ul><ul><ul><li>The process of finding the desired information from large database </li></ul></ul></ul>Knowledge Discovery Process
  8. 10. Knowledge Discovery Process <ul><li>Example: the database of a magazine publisher which sells five types of magazines – on cars, houses, sports, music and comics </li></ul><ul><ul><li>Data mining: </li></ul></ul><ul><ul><ul><li>Find interesting categorical properties </li></ul></ul></ul><ul><ul><li>Questions: </li></ul></ul><ul><ul><ul><li>What is the profile of a reader of a car magazine? </li></ul></ul></ul><ul><ul><ul><li>Is there any correlation between an interest in cars and an interest in comics? </li></ul></ul></ul><ul><li>The knowledge discovery process consists of six stages </li></ul>
  9. 11. Data Selection <ul><li>Select the information about people who have subscribed to a magazine </li></ul>
  10. 12. <ul><li>Pollutions: Type errors , moving from one place to another without notifying change of address, people give incorrect information about themselves </li></ul><ul><ul><li>Pattern Recognition Algorithms </li></ul></ul>Cleaning
  11. 13. <ul><li>Lack of domain consistency </li></ul>Cleaning
  12. 14. Enrichment <ul><li>Need extra information about the clients consisting of date of birth, income, amount of credit, and whether or not an individual owns a car or a house </li></ul>
  13. 15. <ul><li>The new information need to be easily joined to the existing client records </li></ul><ul><ul><li>Extract more knowledge </li></ul></ul>Enrichment
  14. 16. <ul><li>We select only those records that have enough information to be of value (row) </li></ul><ul><li>Project the fields in which we are interested (column) </li></ul>Coding
  15. 17. <ul><li>Code the information which is too detailed </li></ul><ul><ul><li>Address to region </li></ul></ul><ul><ul><li>Birth date to age </li></ul></ul><ul><ul><li>Divide income by 1000 </li></ul></ul><ul><ul><li>Divide credit by 1000 </li></ul></ul><ul><ul><li>Convert cars yes-no to 1-0 </li></ul></ul><ul><ul><li>Convert purchase date to month numbers starting from 1990 </li></ul></ul><ul><ul><ul><li>The way in which we code the information will determine the type of patterns we find </li></ul></ul></ul><ul><ul><ul><li>Coding has to be performed repeatedly in order to get the best results </li></ul></ul></ul>Coding
  16. 18. <ul><li>The way in which we code the information will determine the type of patterns we find </li></ul>Coding
  17. 19. <ul><li>We are interested in the relationships between readers of different magazines </li></ul><ul><ul><li>Perform flattening operation </li></ul></ul>Coding
  18. 20. <ul><li>We may find the following rules </li></ul><ul><ul><li>A customer with credit > 13000 and aged between 22 and 31 who has subscribed to a comics at time T will very likely subscribe to a car magazine five years later </li></ul></ul><ul><ul><li>The number of house magazines sold to customers with credit between 12000 and 31000 living in region 4 is increasing </li></ul></ul><ul><ul><li>A customer with credit between 5000 and 10000 who reads a comics magazine will very likely become a customer with credit between 12000 and 31000 who reads a sports and a house magazine after 12 years </li></ul></ul>Data mining
  19. 21. Knowledge Discovery Process
  20. 22. Business-Question-Driven Process
  21. 23. Data Mining and Business Intelligence Increasing potential to support business decisions End User Business Analyst Data Analyst DBA Making Decisions Data Presentation Visualization Techniques Data Mining Information Discovery Data Exploration OLAP, MDA Statistical Analysis, Querying and Reporting Data Warehouses / Data Marts Data Sources Paper, Files, Information Providers, Database Systems, OLTP
  22. 24. Architecture of a Typical Data Mining System
  23. 25. Data Mining: On What Kind of Data? <ul><li>Relational databases </li></ul><ul><li>Data warehouses </li></ul><ul><li>Transactional databases </li></ul><ul><li>Advanced DB and information repositories </li></ul><ul><ul><li>Object-oriented and object-relational databases </li></ul></ul><ul><ul><li>Spatial databases </li></ul></ul><ul><ul><li>Time-series data and temporal data </li></ul></ul><ul><ul><li>Text databases and multimedia databases </li></ul></ul><ul><ul><li>Heterogeneous databases </li></ul></ul><ul><ul><li>WWW </li></ul></ul>