Major Issues in Data Mining
V. Saranya
AP/CSE
Sri Vidya College of Engineering & Technology, Virudhunagar
• Issues
– Mining Methodology
– User interaction
– Performance
– Data types.
Mining Methodology & User
Interaction Issues
1. Mining different kinds of knowledge in
database.
 Different users-differe...
2. Interactive Mining of knowledge at multiple
levels of abstraction.
 Focus the search patterns.
 Different angles.
4. Data mining query languages and ad hoc
data mining
 High level data mining query language
 Conditions and constraints.
3. Incorporation of background knowledge.
 Background & Domain knowledge.
5. Presentation and visualization of data mining
results.
 Use visual representations.
 Expressive forms like graph, cha...
Performance Issues
• Efficiency and scalability of data mining algorithms.
Running time.
Should be opt for huge amount o...
Diversity of data Types Issues
• Handling of relational and complex types of
data.
One system-> to mine all kinds of data...
Major issues in data mining
Upcoming SlideShare
Loading in …5
×

Major issues in data mining

18,119 views

Published on

Published in: Education, Technology
  • mam....very useful details...mam...thank u..
       Reply 
    Are you sure you want to  Yes  No
    Your message goes here

Major issues in data mining

  1. 1. Major Issues in Data Mining V. Saranya AP/CSE Sri Vidya College of Engineering & Technology, Virudhunagar
  2. 2. • Issues – Mining Methodology – User interaction – Performance – Data types.
  3. 3. Mining Methodology & User Interaction Issues 1. Mining different kinds of knowledge in database.  Different users-different knowledge-different way (with same database)
  4. 4. 2. Interactive Mining of knowledge at multiple levels of abstraction.  Focus the search patterns.  Different angles.
  5. 5. 4. Data mining query languages and ad hoc data mining  High level data mining query language  Conditions and constraints.
  6. 6. 3. Incorporation of background knowledge.  Background & Domain knowledge.
  7. 7. 5. Presentation and visualization of data mining results.  Use visual representations.  Expressive forms like graph, chart, matrices, curves, tables, etc… 6. Handling noisy or incomplete data.  Confuse the process  Over fit the data (apply any outlier analysis, data cleaning methods) 7.Pattern evaluation- the interestingness problem.  Pattern may be uninteresting to the user.  Solve by user specified constraints.
  8. 8. Performance Issues • Efficiency and scalability of data mining algorithms. Running time. Should be opt for huge amount of data. • Parallel, Distributed and incremental mining algorithms. Huge size of database Wide distribution of data High cost Computational complexity Data mining methods Solve by; efficient algorithms.
  9. 9. Diversity of data Types Issues • Handling of relational and complex types of data. One system-> to mine all kinds of data Specific data mining system should be constructed. • Mining information from heterogeneous databases and global information systems.  Web mining uncover knowledge about web contents, web structure, web usage and web dynamics

×