IT326 - Ch1

1 Introduction
IT 326: Data Mining

First Semester 2020-2021
Chapter 1, “Data Mining: Concepts and Techniques” (3rd ed.)

Outline
2
 Why Data Mining?

 What Is Data Mining?
 Knowledge Discovery (KDD) Process
 Data Mining Tasks
 Data Mining Functions
 Summary
Why Data Mining?
3
 The Explosive Growth of Data: from terabytes to petabytes

 Data collection and data availability
◼ Automated data collection tools, database systems, Web, computerized society
 Major sources of data:
◼ Business: Web, e-commerce, transactions, stocks, …
◼ Science: Remote sensing, bioinformatics, scientific simulation, …
◼ Society and everyone: news, digital cameras, YouTube
 We are drowning in data, but starving for knowledge!
 Data mining → Automated analysis of massive data sets
Data Mining – interdisciplinary
4
What is Data Mining?
5
 Data mining (knowledge discovery from data)

 Extraction of interesting (non-trivial, implicit, previously unknown and potentially
useful) patterns or knowledge from huge amount of data.
 Alternative names:
 Knowledge discovery (mining) from data (KDD), knowledge extraction,
data/pattern analysis, business intelligence, etc...
What is Data Mining?
What is the difference between data mining and database query?
Database Query Data Mining Tasks
 Find all credit applicants with last  Find all credit applicants who are high
name of Smith. credit risks. (classification)
 Identify customers who have  Identify customers with similar buying
purchased more than $10,000 in the habits. (Clustering)
last month.  Find all items which are frequently
 Find all customers who have purchased with milk. (association rules)
purchased milk
6
Knowledge Discovery (KDD) Process
7
 Data mining plays an essential role in the knowledge discovery process:

1. Data collection
Data selection
Data Pre-processing
2.
3. Data cleaning
4. Data integration
5. Data transformation Data Pre-processing
6. Data mining
7. Pattern evaluation
8. Knowledge presentation
Data Mining Tasks
8
 Two main types of data mining tasks:

 Descriptive mining tasks characterize properties of the data in a target data set.
 Predictive mining tasks perform induction on the current data in order to predict
values of new data.
 Data mining functions are used to specify the kinds of patterns to be
found in data mining tasks.
Data Mining Functions
Frequent Outlier
Classification Clustering Pattern and Analysis
[Predictive] [Descriptive] Association
[Descriptive] [Predictive]
A simple metaphor for the concept of classification
9
Build a model Testing Data

2
Training data 3
Use the testing data to
Model evaluate the model
1
Learn and analyze the
features of the data
All data are labeled
(Shape is known)
? New Data
4 All data are unlabeled
Use the model to predict the (Shape is unknown)
unknown shape of new data
Classification
10
 Classification is the process of finding a

model (or function) that describes and
distinguishes data classes or concepts.
 The model is derived based on the analysis
of a set of training data (i.e., data objects
for which the class labels are known).
 The model is used to predict the class label
of objects for which the class label is
unknown.
Classification: Application
11
 Direct Marketing:
 Goal: Reduce cost of mailing/advertising by targeting a set of consumers likely to
buy a new product.
 Approach:
◼ Use the data for a similar product introduced before. We know which customers decided to buy
and which decided otherwise. This {buy, don’t buy} decision forms the class label.
◼ Collect various demographic, lifestyle, and company-interaction related information about all
such customers.
◼ Type of business, where they stay, how much they earn, etc…
◼ Use this information as input attributes to train a classifier model.
Kids Sorting\grouping game as a problem of clustering
12
Ungrouped (clustered)
data
Group by color
Analyze the Grouping result

features of the data and how items
are similar
then
try to find the BEST How many clusters we have?
grouping(clustering) of data (items)
Is this the only\best way of grouping?

Clustering
13
 Clustering analyzes data objects

without labels.
 can be used to generate class labels
for a group of objects.
 The objects are clustered or
grouped based on the similarity.
 That is, clusters of objects are formed
so that objects within a cluster have
high similarity in comparison to one
another, but are rather dissimilar to
objects in other clusters.
Clustering: Application
14
 Market Segmentation:
 Goal: subdivide a market into distinct subsets of customers where any subset may
conceivably be selected as a market target to be reached with a distinct
marketing mix.
 Approach:
◼ Collect different attributes of customers based on their geographical and lifestyle related
information.
◼ Find clusters of similar customers.
◼ Measure the clustering quality by observing buying patterns of customers in same cluster vs.
those from different clusters.
Frequent patterns, Association and Correlation Analysis
15
 Frequent patterns are patterns that occur frequently in data.

 Mining frequent patterns leads to the discovery of interesting associations and
correlations within data.
 Example: What items are frequently purchased together in the supermarket?
Association rule:
Transactional Data
Bread → Milk [ 50%, 75%]
Support= 50%
(means that 50% of all the transactions under analysis show
that bread and milk are purchased together).
Confidence= 75%
(means that if a customer buys Bread, there is a 75% chance
that she will buy Milk as well.)
Outlier Analysis
16
 Outlier: A data object that does not comply with the general behavior of
the data.
 Useful in fraud detection, and rare events analysis.
 Example: “Find unusual activity in a client’s banking transactions”?
Outlier analysis may uncover fraudulent usage of credit cards by detecting purchases of
unusually large amounts for a given account number in comparison to regular charges
incurred by the same account. Outlier values may also be detected with respect to the
locations and types of purchase, or the purchase frequency.
Summary
17
 Data mining is the discovery of interesting patterns and knowledge from

massive amount of data.
 A KDD process includes data cleaning, data integration, data selection,
transformation, data mining, pattern evaluation, and knowledge
presentation.
 Mining can be performed in a variety of data.
 Data mining functions: classification, clustering, association and outlier
analysis.

IT326 - Ch1

Uploaded by

Copyright:

Available Formats

IT326 - Ch1

Uploaded by

Document Information

Original Description:

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

IT326 - Ch1

Uploaded by

Copyright:

Available Formats

1 Introduction

IT 326: Data Mining

Chapter 1, “Data Mining: Concepts and Techniques” (3rd ed.)

 Why Data Mining?

 The Explosive Growth of Data: from terabytes to petabytes

 Data mining (knowledge discovery from data)

Database Query Data Mining Tasks

 Data mining plays an essential role in the knowledge discovery process:

 Two main types of data mining tasks:

Build a model Testing Data

 Classification is the process of finding a

Analyze the Grouping result

Is this the only\best way of grouping?

 Clustering analyzes data objects

 Frequent patterns are patterns that occur frequently in data.

 Data mining is the discovery of interesting patterns and knowledge from

You might also like