DATA MINING

1
DATA MINING

• Presented by
• Kalyan K Beemanapalli
• Aditya K Grandhi

2
Outline

• Introduction, Definition, Technology Overview
• A Small Example
• Applications
• Future Applications
• Business Value
• Issues and Concerns
• References

3
Definition, Introduction

• History of Data Mining
• An information extraction activity whose goal is
  to discover hidden facts contained in databases.
• Statistical Analysis Vs Data Mining
• Data mining, in many ways, is fundamentally the
  adaptation of machine learning techniques to
  business applications.

4
Overview
5
Technology Overview

• Association If a customer buys snacks, there is
  a 85 probability that the customer will also buy
  soft drinks or beer.
• Classification Classifications look at the
  behavior and attributes of already determined
  groups
• Sequence a person who buys a washing machine may
  also buy a clothes dryer within six months with a
  probability of 0.7
• Clustering Clustering divides items into groups
  based on the similarities the data mining tool
  finds

6
Market Basket Analysis

• 80 of the people who buy milk also buy bread
• On Fridays, 70 of the men who bought diapers
  also bought beer.
• What is the relationship between diapers and
  beer?
• Walmart could trace the reason after doing a
  small survey!

7
Role of Domain Knowledge

• Informal knowledge about application
• domain can be formalized into a set of
• Domain Knowledge Elements
• What is Domain Knowledge?
• Why Domain Knowledge is relevant in
• the case of Data Mining?
• ? The present algorithms just mine the data and
• ask domain experts to decide the
• interestingness of the results.
• ? Can Data mining algorithms be improved to
• use the knowledge possessed by
• domain experts?
• 
  
  

Knowledge
8
Applications of Data Mining

• CRM - allow you to determine who your
• best customers are and why.
• Forecasting - Forecasting tools allow users to
  collect data, find patterns in that data and then
  predict future events or behaviors
• Online Fraud Detection
• e-Business Intelligence
• The list is not exhaustive.

9
Future Applications

• Network Intrusion Detection
• Researchers in Computer Science are concentrating
  on including the domain knowledge into the data
  mining algorithms
• Example Exploring the HR domain in an
  organization

10
Business Value

• Venkataramans Architecture This technology has
  the potential to affect the Business Scope of an
  organization
• Amazons case
• ? 20 for advertisement 80 for customer
  experience

11
Issues and Concerns

• Privacy Concerns In the light of developments in
  technology to analyze personal data, public
  concerns regarding privacy are rising PPDM
  workshop
• ? Example An insurance can decide its policy
  just by knowing your social security number
• Security,Ethical and legal issues An individual
  country's legal system may prevent sharing of
  customer data between a subsidiary and its parent
• Interesting Observation How do you quantify
  Privacy?

12
References

• http//www.aaai.org/AITopics/html/ethics.html
• http//businessintelligence.ittoolbox.com/
• http//www.ipc.on.ca/docs/datamine.pdf
• http//www.centeronline.org/knowledge/article.cfm?
  ID843ContentProfileID123374Actionsearching

13

• Questions?