Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Scribd Logo
Upload

Welcome to Scribd!

  • 54 views

    Vinee

    Uploaded by

    vineesha28
    This document provides an overview of data mining techniques including classification, clustering, regression, and association rules. It explains that data mining allows extraction of hidden patterns from large data sets to help businesses gain insights. However, effective data mining requires linking multiple data sources which can raise privacy concerns if it allows reconstructing complete customer histories from different databases.

    Copyright:

    Attribution Non-Commercial (BY-NC)
    Download as PPTX, PDF, TXT or read online from Scribd

    Vinee

    Uploaded by

    vineesha28
    54 views28 pages
    This document provides an overview of data mining techniques including classification, clustering, regression, and association rules. It explains that data mining allows extraction of hidden patterns from large data sets to help businesses gain insights. However, effective data mining requires linking multiple data sources which can raise privacy concerns if it allows reconstructing complete customer histories from different databases.

    Original Title

    vinee ppt

    Copyright

    © Attribution Non-Commercial (BY-NC)

    Available Formats

    PPTX, PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    This document provides an overview of data mining techniques including classification, clustering, regression, and association rules. It explains that data mining allows extraction of hidden patterns from large data sets to help businesses gain insights. However, effective data mining requires linking multiple data sources which can raise privacy concerns if it allows reconstructing complete customer histories from different databases.

    Copyright:

    Attribution Non-Commercial (BY-NC)
    Download as PPTX, PDF, TXT or read online from Scribd
    Download as pptx, pdf, or txt
    54 views28 pages

    Vinee

    Uploaded by

    vineesha28
    This document provides an overview of data mining techniques including classification, clustering, regression, and association rules. It explains that data mining allows extraction of hidden patterns from large data sets to help businesses gain insights. However, effective data mining requires linking multiple data sources which can raise privacy concerns if it allows reconstructing complete customer histories from different databases.

    Copyright:

    Attribution Non-Commercial (BY-NC)
    Download as PPTX, PDF, TXT or read online from Scribd
    Download as pptx, pdf, or txt
    You are on page 1of 28

    P M

    Overview
    Introduction
    Explanation of Data Mining Techniques Advantages

    Applications
    Privacy

    EXTRACTING DATAMINING: THE KNOWLWDGE FROM THE DATA B

    KDD: KDD stands forKNOWLEDGE DISCOVER DATA BASE KDD identify the invisible correlation

    Data collection(1960):using

    coumputers,tapes and disks


    Data access(1980):using RDBMS,SQL

    Data warehouse&decision

    support(1990):using OLAP,DWH, Data mining(today):using advanced algorithms,micro processors etc

    Data Warehousing
    Data Warehouse:
    is a repository (or archive) of information

    gathered from multiple sources, stored under a unified schema, at a single site.
    Collect data Store in single repository Allows for easier query development as a single repository can be

    queried.

    DATA WAREHOUSING:

    Data warehousing has some OLAP operations OLAP stands for OnlineAnalyticalProcess It stores the historical data It performs only read pattern It deals with the long term operations OLAP operations are rollup

    drill down slicing dicing


    It has high flexibility and it consists less no.of users It is subject-oriented

    OLAP - On-line Analytical Processing Provides you with a very good view of what is happening, but can not predict what will happen in the future or why it is happening

    1.Data Cleaning 2.Data Integration 3.Data Transformation 4.Data Reduction

    Discovery of Knowledge

    Steps:
    Business Understanding: what problem are we trying to

    solve? What is the business trying to achieve? Data Understanding: do we have the data to be able to answer this questions? If not, what is the cost of acquiring that additional information? Data Preparation: all data is dirty and needs to be cleaned and transformed. This is the heavy lifting stage. Analysis & Modeling: the tools must be chosen based on what the business is trying to understand and the data available. Evaluate Outcomes: how well does the model actually works from a statistical point of view (significance) and from a business point of view (actionability)? Deployment: driving the insight into the business.

    Data Mining Techniques


    Classification
    Clustering Regression

    Association Rules

    Classification: Given a set of items that have several classes,

    Classification (training instances) with their and given the past instances
    associated class, Classification is the process of predicting the class of a new item. Therefore to classify the new item and identify to which class it belongs Example: A bank wants to classify its Home Loan Customers into groups according to their response to bank advertisements. The bank might use the classifications Responds Rarely, Responds Sometimes, Responds Frequently. The bank will then attempt to find rules about the customers that respond Frequently and Sometimes. The rules could be used to predict needs of potential customers.

    Technique for Classification


    Decision-Tree Classifiers
    Job
    Engineer

    Doctor

    Carpenter

    Income
    <30K >50K <40K

    Income
    >90K

    Income
    <50K >100K

    Bad

    Good

    Bad

    Good

    Bad

    Good

    Predicting credit risk of a person with the jobs specified.

    Clustering

    Clustering algorithms find groups of items that are similar. It divides a data set so that records with similar content are in the same group, and groups are as different as possible from each other. (2)
    Example: Insurance company could use clustering to group clients by their age, location and types of insurance purchased. The categories are unspecified and this is referred to as unsupervised learning

    Regression
    Regression deals with the prediction of a value, rather than a class.
    Example: Find out if there is a relationship

    between smoking patients and cancer related illness. It removes the noisy data Given values: X1, X2... Xn Objective predict variable Y One way is to predict coefficients a0, a1, a2
    Y = a0 + a1X1 + a2X2 + anXn

    Regression
    Example graph:
    Line of Best Fit Curve Fitting

    Association Rules
    An association algorithm creates rules that describe

    how often events have occurred together. (2)


    Example: When a customer buys a hammer, then 90%

    of the time they will buy nails. Ex: computer=>antivirussoftware[support=2%,confidence=60%]. Support ex: (A=>B)=P(AUB) Confidence ex:(A=>B)=P(B/A)

    Association Rules
    Support: is a measure of what fraction of the

    population satisfies both the antecedent and the consequent of the rule Support is the measure in rule of interestingness. Support is 2% means that 2% of the transaction under analysis show that computer and antivirus are purchased together

    Association Rules
    Confidence: is a measure of how often the

    consequent is true when the antecedent is true. It is the measure ot rule of interestingness Example: Confidence is 60% that means 60% of the customer who purchased the computer also purchase the software

    ADVANTAGES:
    Provides new knowledge from existing data
    Public databases Government sources Company Databases

    Old data can be used to develop new knowledge

    Weatherforecast Insurance Government Health care New knowledge can be used to improve services or products

    Improvements lead to:


    Bigger profits More efficient service

    Uses of Data Mining


    Sales/ Marketing
    Diversify target market
    Identify clients needs to increase response rates

    Risk Assessment
    Identify Customers that pose high credit risk

    Fraud Detection
    Identify people misusing the system. E.g. People who

    have two Social Security Numbers

    Customer Care
    Identify customers likely to change providers Identify customer needs

    Financial data analysis

    industry manufacturing
    Telecommunicationb industry
    Biological data analysis Scientific application

    Retail

    Intrusion detection

    What data mining has done for...


    Scheduled its workforce to provide faster, more accurate answers to questions.

    Reduced direct mail costs by 30% while garnering 95% of the campaigns revenue.

    Applications of Data Mining


    (4)

    Source IDC 1998

    Privacy Concerns

    Effective Data Mining requires large sources of data To achieve a wide spectrum of data, link multiple data sources Linking sources leads can be problematic for privacy as follows: If the following histories of a customer were linked:
    Shopping History Credit History Bank History Employment History

    The users life story can be painted from the

    collected data

    References
    Silberschatz, Korth, Sudarshan, Database System Concepts, 5th Edition, Mc Graw Hill, 2005 2. http://www.twocrows.com/glossary.htm, Two Crows, Data Mining Glossary 3. http://en.wikipedia.org/wiki/Data_mining, Wikipedia 4. http://phoenix.phys.clemson.edu/tutorials/exce l/regression.html 5. http://wwwmaths.anu.edu.au/~steve/pdcn.pdf
    1.

    You might also like