Scribd
Upload
102 views14 pages

Data Mining

Data mining is the process of extracting hidden predictive information from large datasets. It has evolved from data collection in the 1960s, to data access in the 1980s, data warehousing and decision support in the 1990s, and is now emerging as data mining. The goals of data mining are prediction, identification, classification, and optimization. It has applications in marketing, finance, manufacturing, healthcare, and web personalization to gain insights from data.

Uploaded by

Gyandeep Tripathi
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
102 views14 pages

Data Mining

Data mining is the process of extracting hidden predictive information from large datasets. It has evolved from data collection in the 1960s, to data access in the 1980s, data warehousing and decision support in the 1990s, and is now emerging as data mining. The goals of data mining are prediction, identification, classification, and optimization. It has applications in marketing, finance, manufacturing, healthcare, and web personalization to gain insights from data.

Uploaded by

Gyandeep Tripathi
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 14

DATA MINING

DEFINITION
 Data mining, the extraction of hidden predictive
information from large databases, is a powerful
new technology with great potential to help
companies focus on the most important
information in their data warehouses.
EVOLUTIONARY STEP
 Data Collection (1960s)
 Data Access (1980s)
 Data Warehousing & Decision Support(1990s)
 Data Mining (Emerging Today)
GOALS OF DATA MINING

 Prediction
 How certain attributes within the data behave in future.
 Identification
 Data patterns used to identify the existence of an item, an event
or an activity.
 Classification
 Data partition to identify different classes or patterns based on
combination of parameters.
 Optimization
 Optimize the use of limited resources like time, space, money or
material and maximize sale & profit under given constraints.
PREDICTION

 What customers buy with discount.


 How much sale value a store generates in a given
period.
 Whether deleting a sale line yield more profit.
 Uses techniques like Regression, correlation etc.
IDENTIFICATION

 Intruders trying to break the computer system


may be identified by the program executed, files
accessed and CPU time per session.
 Existence of gene is identified by certain
sequence of nucleotide symbols present in the
DNA sequence.
 Authentication
CLASSIFICATION

 Customers can be identified as discount seekers,


shoppers in a rush, loyal regular customers,
shoppers attached to name brands etc.
 Classification can help in categorizing food as
health food, party food, school lunch food etc.
LEVELS OF ANALYSIS
 Regression
 Decision Trees
 Nearest Neighbor Classification
 Neural Networks
 Rule Induction –If - else - then
TECHNOLOGICAL INFRASTRUCTURE
REQUIRED
 Depends on
 Size of the database
 Query complexity

 Relational database storage


 extensive indexing capabilities
 Massively Parallel Processors (MPP)
APPLICATIONS OF DATA MINING

 Marketing
 Consumer behavior based on buying pattern
 Determination of market strategy
 Targeted mailing
 Advertisement campaigns
 Design of catalogue
 Store layout
APPLICATIONS OF DATA MINING CONT..
 Finance
 Analysis of trustworthiness of a client
 Segmentation of account receivables
 Performance analysis of financial investments like
stocks, bonds & mutual funds
 Evaluation of financing options
 Fraud detection
APPLICATIONS OF DATA MINING CONT..
 Manufacturing
 Optimization of resources like machine, manpower &
material
 Optimal design of manufacturing processes
 Shop floor layout
 Product design
 Packaging design
APPLICATIONS OF DATA MINING CONT..
 Healthcare
 Discovery pattern in radiological images
 Analysis of micro array to relate to diseases
 Analysis of side effects of drugs.
 Effectiveness of certain treatments.
 Optimizing processes within hospitals.
 Relating patients wellness data with doctor’s
qualification.
APPLICATIONS OF DATA MINING CONT..
 Web site personalization
 Credit card fraud detection
 SAS lie detector
 Market based analysis

You might also like