WEKA:Data Mining Whats It All About


Published on

WEKA:Data Mining Whats It All About

Published in: Technology
  • Be the first to comment

  • Be the first to like this

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

No notes for slide

WEKA:Data Mining Whats It All About

  1. 1. Data Mining: What’s It All About<br />
  2. 2. Data as a resource<br />Hidden Patterns<br />Data is unstructured,<br />meaning less<br />contains<br />gives<br />Information<br />Intelligible and useful<br />is<br />
  3. 3. Analysis of data<br />Data being generated is humongous<br />Increased digitization of processes is increasing the rate at which data is being generated<br />Manual analysis of this much data is not possible<br />Computational resources are getting faster and cheaper<br />Therefore analysis of data using computers is the right way ahead: Data mining<br />
  4. 4. Data mining: Definition <br />Data mining makes sense of unstructured data and discover useful, hidden information in the form of patterns<br />Data mining helps in bridging the gap between generation of data and the understanding of data<br />Data<br />Information<br />Data mining<br />
  5. 5. Use case scenarios of Data mining <br />On the web:<br /><ul><li>Amazon uses a technique called collaborative filtering to suggest items which a user might find interesting enough to buy</li></li></ul><li>Data mining in business:<br /><ul><li>Banks and financial institutions uses data mining to check a customers past record before giving him/her credit
  6. 6. Customer is graded on the basis of few past records
  7. 7. Only if the grading satisfies the minimum requirement of the bank, the customer is granted any credit
  8. 8. Retail chains and super market uses data mining to identify the product which are usually bought together, and use this to place their products</li></li></ul><li>Structural Pattern<br />Data mining produces results in the form of rules applicable on the data: Association rules<br />On the basis of few attributes data mining rules predict the value of an attribute: Classification rules <br />Consider the example of weather forecasting. Few of the structural rule (classification rule) derived are:<br />If outlook = sunny and humidity = high then play = no<br /> If outlook = rainy and windy = true then play = no<br /> If outlook = overcast then play = yes <br />
  9. 9. Data mining in weather forecasting<br /><ul><li>Here we can use classification rules to predict if the playing conditions are appropriate or not, i.e. attribute play using the attribute set: {outlook, temperature, humidity, windy}
  10. 10. We can also analyze the data to derive association rules present in the data</li></li></ul><li>Data mining and ethics<br />There might be some instances on the basis of race, sex, religion and so on which have been derived indirectly from the data<br />People need to know about how the data they are providing about them self will be used<br />Data which is being stored for data mining purposes should be kept confidential and its integrity should be maintained<br />What were the ecological conditions under which data was <br />collected<br />
  11. 11. Visit more self help tutorials<br />Pick a tutorial of your choice and browse through it at your own pace.<br />The tutorials section is free, self-guiding and will not involve any additional support.<br />Visit us at www.dataminingtools.net<br />