BITS Pilani
[Link] Malapati
BITS Pilani Asst Professor
Department of CSIS
Hyderabad Campus
BITS Pilani
Hyderabad Campus
Data Mining - Introduction
Today’s Learning objective
• Define what is Data Mining
• List the Steps/Phases involved in data Mining
• Compare DBMS,OLAP and Data Mining
• List the Predictive and Descriptive Data Mining Tasks
BITS Pilani, Hyderabad Campus
DIKW Pyramid
BITS Pilani, Hyderabad Campus
Data generated from several
sources
BITS Pilani, Hyderabad Campus
Dreaded with data
BITS Pilani, Hyderabad Campus
What is Data Mining?
Searching for knowledge
from your data.
BITS Pilani, Hyderabad Campus
What is Data Mining?
• Data mining – Extraction of interesting (non-trivial,
implicit, previously unknown and potentially useful)
patterns or knowledge from huge amount of data.
• Alternative names – Knowledge discovery (mining) in
databases (KDD), knowledge extraction, data/pattern
analysis, etc.
BITS Pilani, Hyderabad Campus
Data Mining Process
BITS Pilani, Hyderabad Campus
DBMS,OLAP and Data Mining
DBMS OLAP DATA MINING
TASK Extract data Summaries, trends Knowledge
and forecasts Discovery of
hidden patterns
Type of Result Information Analysis Insight &
Prediction
Method Deduction Multidimensional Induction
data modelling,
Aggregation,
Statistics
Example List all What is the average Who will buy
customers who income of printers along with
purchased customers across computers?
Computers in regions?
the last year.
BITS Pilani, Hyderabad Campus
Data Mining Tasks
Objective is to predict the value of a particular
attribute based on the values of other attributes. Classification
Predictive Regression
Data Outlier Detection
Mining
Descriptive Clustering
Association
Objective is to derive patterns
Sequential Pattern
Mining
BITS Pilani, Hyderabad Campus
Classification Example
Tid Home Marital Taxable Home Marital Taxable
Owner Status Income Default Owner Status Income Default
1 Yes Single 125K No No Single 75K ?
2 No Married 100K No Yes Married 50K ?
3 No Single 70K No No Married 150K ?
4 Yes Married 120K No Yes Divorced 90K ?
5 No Divorced 95K Yes No Single 40K ?
6 No Married 60K No No Married 80K ? Test
10
Set
7 Yes Divorced 220K No
8 No Single 85K Yes
9 No Married 75K No
Training
10 No Single 90K Yes Model
10
Set
BITS Pilani, Hyderabad Campus
Classification: Definition
• Given a collection of records (training set )
– Each record contains a set of attributes, one of the attributes is the
class.
• Find a model for class attribute as a function of the values
of other attributes.
• Goal: previously unseen records should be assigned a
class as accurately as possible.
– A test set is used to determine the accuracy of the model. Usually,
the given data set is divided into training and test sets, with training
set used to build the model and test set used to validate it.
BITS Pilani, Hyderabad Campus
Regression
• For classification the output(s) is nominal
• In regression the output is continuous
– Function Approximation
• Many models could be used – Simplest is linear regression
– Fit data with the best hyper-plane which "goes through"
the points y
dependent
variable
(output)
x – independent variable (input)
BITS Pilani, Hyderabad Campus
Clustering
BITS Pilani, Hyderabad Campus
Association Rule Mining
BITS Pilani, Hyderabad Campus
Sequential Pattern Mining
• Given a set of sequences and support threshold, find the
complete set of frequent subsequences
A sequence : < (ef) (ab) (df) c b >
A sequence database
SID sequence An element may contain a set of items.
10 <a(abc)(ac)d(cf)> Items within an element are unordered
and we list them alphabetically.
20 <(ad)c(bc)(ae)>
30 <(ef)(ab)(df)cb> <a(bc)dc> is a subsequence
40 <eg(af)cbc> of <a(abc)(ac)d(cf)>
Given support threshold min_sup =2, <(ab)c> is a
sequential pattern
BITS Pilani, Hyderabad Campus
Challenges in Data Mining
• Tremendous amount of data
• Algorithms must be highly scalable to handle such as
tera-bytes of data
• High-dimensionality of data
• Micro-array may have tens of thousands of
dimensions • High complexity of data
• Noisy and unreliable
• Dynamically evolving
• High dimensionality
• Multiple heterogeneous sources
• New and sophisticated applications
BITS Pilani, Hyderabad Campus
Teaching and Evaluation for
BITS F415 – L P U 3 0 3
Evaluation Scheme:
Nature of
Component Duration Weightage (%)
Component
Mid Term Exam 90 Mins. 25 Closed Book
Quizzes (Three) 30 Mins 15 Closed Book
Assignments -- 25 Open Book
Comprehensive 3 Hours 35 Closed Book
Chamber Consultation Hour: Mon 8th hour
Notices: All notices pertaining to this course will be displayed on the CMS/ CSIS Notice
Board.
Make-up Policy: Prior Permission is must and Make-up shall be granted only in genuine
cases based on individual’s need, circumstances. The recommendation from chief warden is
necessary to request for a make-up.
BITS Pilani, Hyderabad Campus
Books
TEXT BOOK REFERENCE BOOKS
BITS Pilani, Hyderabad Campus
Take home message
• Data Mining refers to non-trivial extraction of implicit,
previously unknown and potentially useful knowledge from
data
• Data Mining covers topics including warehousing,
association analysis, clustering, classification, anomaly
detection, etc. (based on the type of mined knowledge), as
well as transaction data mining, stream data mining,
sequence data mining, graph data mining, etc. (based on
the type of data)
• Data Mining has wide applications in many different fields in
business, science, engineering, education, and many more
BITS Pilani, Hyderabad Campus
