Data Mining

Unit - 01
DATA MINING
Data: - It is a collection of raw facts, which doesn't have a perfect meaning.
Information: - It is a processed data or meaningful data which have a perfect meaning.
Database: - It is an organised collection of related data, so that it can be easily accessed managed and
updated.
DBMS: - Database management system is a software or collection of program which enables us to store,
modify and extract information from database.
Data Mining: - Data mining in general terms means "Digging or Mining or extraction deep into the data
which is in different form to gain patterns and to gain knowledge on that pattern.
OR
It is a process of discovering or Mining or extracting knowledge from large amount of data.
In the process of data mining, large data sets are first stored then patterns are identified and relationship is
established to perform data analysis and solve problems.
What is Data Mining used for?
1. Data mining is a process used by companies to turn raw data into Useful information by using software
to look for patterns in large batches of data, business can learn more about their customers to develop more
effective marketing strategies, increases sales and decreases costs.
2. The volume of information is increasing every day that we can handle from business transactions,
scientific data, sensor data, pictures, videos, etc. So, we need a system that will be capable of extracting
the essence of information available and that can automatically generate reports, views or summaries of
data for better decision making.
3. Data mining is used in business to make better managerial decisions by:
 Automatic summarisation of data
 Discovering patterns in raw data
 Extracting the essence of information Stored.
Data Mining Types: Data mining has several types including

 Pictorial data mining

 Text mining
 Social media mining
 Web mining
 Audio and video mining amongst others.
Applications of Data Mining:
1. Sales/ Marketing: Data mining enables business to understand the hidden patterns inside historical
purchasing transaction data, thus helping in Planning and launching new marketing campaigns in a
prompt and cost effective way.

Shridevi Degree College,Tumkur Page 1

 Data Mining
2. Healthcare:-
 Data mining is used for classification of diseases. It is also used to find the relationships
between diseases and the effectiveness of treatments.
 That is used to identify new drugs or to ensure that patients receive appropriate timely care. It is
also supports Healthcare, insurance companies in detecting fraud and abuse.
3. Education: - Data mining is used to predict students future, learning behaviour of students, predict the
results of students. Based on the results, the institution can focus on what to teach and how to teach.
Learning pattern of the students can be captured. Data mining is used to develop techniques to teach
them.
4. Banking: - Banking industry has hugely beneficial from advancements in digital technology. Data
mining is used in financial and banking sector for credit analysis, fraudent transaction, cache
management and to predict payments.
5. Retail Industry: - data mining has its great application in Retail Industry because it collects large
amount of data from sales, customer purchasing history, goods transportation, consumption and
services.
Data mining helps in identifying customer buying patterns and Trends that leads to improved quality of
customer service and good customer retention and satisfaction.
6. Transportation: - data mining helps determine the distribution schedules among warehouses and
outlets and analyse loading patterns.
7. E-commerce: - many E-Commerce sites used data mining to offer cross-selling and upselling of their
products. The shopping sites such as Amazon, Flipkart show “people also viewed ",” frequently bought
together “to the customers who are interacting with the site.
8. Farming: - farmers use data mining to find out the yield of vegetables with the amount of water
required by the plants.

Data Mining Architecture/Components:

1. Data Warehouse: A data warehouse is a place with stored information collected from the multiple
sources un- unified schema.
Information stored in a data warehouse is critical to organization for the process of decision
making.
2. Database or Data Warehouse Server: The server is a place that holds all the data which is ready to
be processed. The fetching of data works up on the user's request and thus the actual datasets can be very
personal.
3. Data Mining Engine: it is the core component of data mining process which consists of various
modules that are used to perform various tasks like clustering, classification, and prediction and correlation
analysis.
4. Pattern Evaluation: Pattern evaluation is responsible for finding various patterns with the half of
data mining engine. Example: pie-chart, bar-graph, line-graph, dot matrix.
5. Graphical User Interface: GUI provides communication between users and data mining system, it
allows user to use the system easily even if user doesn't have proper knowledge of the system.
6. Knowledge Base: it consists of data that is very important in the process of data mining. It provides
input to the data mining engine which guides data mining engine in the process of pattern search.

Shridevi Degree College,Tumkur Page 2

 Data Mining

KDD Process (Knowledge Discovery in Database)

It refers to the broad Process of finding knowledge in data, and emphasizes the high-level application of
particular data mining method
Steps: - 1. Data Cleaning
2. Data Integration
3. Data Selection
4. Data Transformation
5. Data Mining
6. Pattern Evaluation
7. Knowledge Representation
1. Data Cleaning: Data cleaning is defined as removal of noisy and irrelevant data form collection.

 Cleaning in case of missing values.

 Cleaning noisy data, where noise is a random or variance error.
 Cleaning with the data discrepancy detection and data transformation tools.
2. Data integration: data integration is defined as heterogeneous data from multiple source combined in a
common source (data warehouse).
 Data integration using data migration tools.
 Data integration using data synchronisation tools.
 Data integration using ETL (Extract-Load-Transformation) process.
3. Data selection: data selection is defined as the process where data relevant to the analysis is decided
and retrieved from the data collection.
 Data selection using neural network
 Data selection using decision trees
 Data selection using naive Bayes.
 Data selection using clustering, regression, etc.

Shridevi Degree College,Tumkur Page 3

 Data Mining

4. Data Transformation: Data transformation is defined as the process of transforming data into
appropriate form required by mining procedure.
Data transformation is a two-step process:

 Data Mapping: Assigning elements from source base to destination to capture

transformations.
 Code Generation: creation of the actual transformation program.
5. Data Mining: Data mining is defined as clever techniques that are applied to extract patterns potentially
useful.
 Transforms task relevant data into patterns.
 Decides purpose of model using classification or characterization.
6. Pattern Evaluation: pattern evaluation is defined, identifying strictly, increasing patterns, representing
knowledge based on the given measures.
 Find interestingness score of each pattern.
 Uses summarisation and visualisation to make data understandable by user.
7. Knowledge Representation: Knowledge representation is defined as technique which utilized
visualisation tools to represent data mining results.
 Generate reports.
 Generate tables.
 Generate discriminants rules, classification rules, characterized rules, etc.
Advantages of KDD
 Improves decision-making
 Increase efficiency
 Better customer service
 Fraud detection
 Predictive modelling

Shridevi Degree College,Tumkur Page 4

 Data Mining
Disadvantages of KDD
 Privacy concerns
 Complexity
 Unintended consequences, such as bias or discrimination, if the data or models are not properly
understood or used.
 Data quality
 High cost

Data Mining Issues:

Data Mining Issues

Mining Methodology & Performance Issues Diverse Data Types Issues

User Interaction

1. Mining Methodology Issues: Methodology-related data mining issues encompass challenges

related to the choice and application of mining algorithms and Techniques. Selecting the right
method for a specific dataset and problem can be daunting.
 Mining different kinds of knowledge in databases: Different Users may be interested in
different kinds of knowledge. Therefore, it is necessary for data mining to cover a broad
range of knowledge discovery task.
 Interactive Mining of knowledge at multiple levels of abstraction: The Data Mining
process needs to be interactive because it allows users to focus the search for patterns,
providing and refining data mining requests based on the returned results.
 Incorporation of background knowledge: To guide discovery process and to express the
discovered patterns, the background knowledge can be used.
 Data mining query languages and ad hoc data mining: Data Mining Query language that
allows the user to describe ad hoc mining tasks, should be integrated with a data warehouse
query language and optimised for efficient and flexible data mining.
 Presentation and visualization of data mining results: Once the patterns are discovered it
needs to be expressed in high level languages, and visual representations. These should be
easily understandable.
 Handling noisy or incomplete data: The data cleaning methods are required to handle the
noise and incomplete objects while mining the data regularities. If the data cleaning methods
are not there then the accuracy of the discovered patterns will be poor.
 Pattern evaluation: The patterns discovered should be interesting because either they
represent common knowledge or lack novelty.

Shridevi Degree College,Tumkur Page 5

 Data Mining
2. Performance Issues :
 Performance-related: Data mining issues revolve around scalability, efficiency, and handling
large datasets. As data volumes continue to grow exponentially, it becomes essential to develop
algorithms and infrastructure capable of processing and analysing data promptly.
 Efficiency and scalability of data mining algorithms: In order to effectively extract the
information from huge amount of data in databases, data mining algorithm must be efficient
and scalable.
 Parallel, distributed, and incremental mining algorithms: The factors such as huge size of
databases, wide distribution of data, and complexity of data mining methods motivate the
development of parallel and distributed data mining algorithms.

3. Diverse Data Types Issue: The Diverse data types data mining issues highlight the complexity of
dealing with heterogeneous data sources.
 Handling of relational and complex types of data: The database may contain complex data
objects, multimedia data objects, spatial data, temporal data etc. It is not possible for one
system to mine all these kind of data.
 Mining information from heterogeneous databases and global information systems: The
data is available at different data sources on LAN or WAN. These data source may be
structured, semi structured or unstructured. Therefore, mining the knowledge from them adds
challenges to data mining.

Data Mining Metrics

It may be defined as a set of measurements which can help in determining the efficiency of the data mining
method/Technique or Algorithm.
They are important to help take the right decision as like as choosing the right data mining technique or
Algorithm.
Ex:
 For web mining the various metrics are website visitors, pages served, in degree or queries in a
given time.
 Accuracy i.e. percentage of correctly classified sample is the metrics for classification tasks.

Social Implications of Data Mining

 The major Social concerns of data mining are the issue of privacy and data security.
 In day to day life/line one uses credit card, debit card, super market loyalty card which help in the
personal profile, information collection.
 Collection of personal data may be beneficial for companies and consumers, there is also potential
for misuse/threat by applying the data mining tools on this collected personal data.
 In this connection, the sensitive data link customer ids are removed before applying data mining
tools.

Shridevi Degree College,Tumkur Page 6

 Data Mining

 In addition, various privacy preserving data mining methods are been developed to handle the issue
of privacy and data security issue.
 We should have domain specific data mining we can provide security, integrity and privacy of data.
Ex: Banking Sector.

Tasks of Data Mining

Data Mining involves six common classes of tasks:
1. Anomaly detection (Outlier/change/deviation detection): The identification of unusual data
records, that might be interesting or data errors that require further investigation.
2. Association rule learning (Dependency modelling): Searches for relationships between variables.
For example a super market might gather data on customer purchasing habits. Using association
rule learning, the super market can determine which products are frequently bought together and
use this information for marketing purposes.
3. Clustering: Clustering is the task of discovering groups and structures in the data that are in some
way or another “similar”, without using unknown structures in the data.
4. Classification: Classification is the task of generalizing known structure to apply to new data. For
example, an E-mail program might attempt to classify an E-mail as “legitimate” or “spam”.
5. Regression: Attempts to find a function which models the data with the least error.
6. Summarisation: Providing a more compact representation of the data set, including visualisation
and report generation.
Challenges of Data Mining
In this section we will explore various challenges of data mining, as mention below:
 Data Quality: Data mining heavily relies on the quality of the input data. Inaccurate, incomplete,
or noisy data can lead to misleading result and hinder the discovery of meaningful patterns.
 Data complexity: Complex datasets with diverse structures, including unstructured data like text
and images, pose significant challenges in the terms of Pre-processing, integration, and analysis.
 Data privacy and security: Safeguarding sensitive information is paramount. Data mining can
potentially compromise privacy if not conducted with stringent privacy - preserving techniques and
compliance with data protection regulations.
 Scalability: As data volumes continue to grow, ensuring that data mining algorithms and
infrastructure can handle large-scale datasets efficiently becomes as pressing issues.
 Interpretability: Understanding and explaining the outcomes of data mining models is crucial for
informed decision-making black-box models can raise concerns when interpretability is required.
 Ethics: Ethical consideration in data mining, such as fairness, bias, and the responsible use of data,
or gaining prominence. Ensuring ethical practices throughout the data mining process is a critical
challenge.

Data Mining Techniques

Data Mining is the Science, art, and technology of discovering large and complex bodies of data in order
to discover useful patterns.
Here different types of Data Mining Techniques which are used to predict desire output.
1) Association: Association analysis is the finding of association rules showing attributes-value
conditions that occurs frequently together in a given set of data. Association analysis is widely used

Shridevi Degree College,Tumkur Page 7

 Data Mining

for a market basket or transaction data analysis. Association rule mining is a significant and
exceptionally dynamic area of data mining research.
One method of association-based classification, called associative classification, consists of
two steps .In the main step, association instructions are generated using a modified version of the
standard association rule mining algorithm known as a Priory. The second step construct a classifier
based on the association rules discovered.
2) Classification: Classification is the processing of finding a set of models or functions that
describes and distinguished data classes or concepts, for the purpose of being able to use the model
to predict the class of objects whose class label is unknown. The determined model depends on the
investigation of a set of training data information (i.e. Data objects whose class label is known).The
derived model may be represented in various forms, such as classifications (if-then) rules,
decisions trees, and neural networks. Data mining has a different types of classifier:
 Decision Tree
 SVM (Support Vector Machine)
 Generalized Linear Models
 Bayesian classification.
 Classification by back propagation
 K-NN classifier
 Rule-based classification
 Frequent -pattern based Classification
 Rough Set Theory
 Fuzzy-Logic.

 Decision Tree: A decision tree is a flow-chart-like tree structure, where each node represents a
test on an attribute value, each branch denotes an outcome of a test, and tree leaves represent classes
or class distribution. Decision trees can be easily transformed into classification rules.
 Support vector machine (SVM) classifier method: Support vector machine is a supervised
learning strategy used for classification and additionally used for regression. When the output of the
support vector machine is a continuous value, the learning methodology is claimed to perform
regression; and once the learning methodology will predict a category label of the input object, it's
known as classification.

 Generalized linear model: Generalized linear model (GLM) is a statistical technique, for linear
modelling. GLM provides extensive coefficient statistics and model statistics, as well as row
diagnostics .It also supports confidence bounds.
 Bayesian classification:Bayesian classifier is a statistical classifier. They can predict class
membership probabilities, for instance, the probability that a given sample belongs to a particular
class. Bayesian classification is created on the bayes theorem. Studies comparing the classification
algorithm have found a simple Bayesian classifiers known as the Naive Bayesian classifier to be
comparable in performance with decision tree and neural network classifiers.
 Classification by back propagation: A back propagation learns by iteratively processing a set of
training samples, comparing the network's estimate for each sample with the actual known class
label. For each training sample, weights are modified to minimize the mean square error between
the network's prediction and the actual class. These changes are made in the "backward" direction.

Shridevi Degree College , Tumkur Page 10

 Data Mining

K-nearest Neighbour (K-NN) classifier method: The k-nearest method (K-NN) classifier is
taken into account as an example-based classifier, which means that the training documents are used
for comparison instead of an exact class illustration, like the class profile utilised by other
classifiers. As such, there's no real training section.
Rule-based classification: Rule-based classification represent the knowledge in the form of
if-then rules. An assessment of a rule evaluated according to the accuracy and coverage of the
classifier. If more than one rule is triggered then we need to conflict resolution in rule-base
classification. Conflict resolution can be performed on three different parameters size ordering, class
based ordering, and rule-based ordering.
Frequent pattern based classification: Frequent pattern discovering (or FP discovery, FB
mining, or frequent item set mining) is part of data mining. It describes the task of finding the most
frequent and relevant patterns in large datasets. The idea was first presented for mining transaction
databases.
Rough set theory: Rough that theory can be used for classification to discover structural
relationships within imprecise or noisy data. It applies to discrete-valued features.
Continuous-valued attributes must therefore be discrete prior to their use.
Fuzzy logic: Fuzzy logic is valuable for data mining frameworks performing
grouping/classification. It provides the benefit of working at a high level of abstraction.
3) Prediction: Data prediction is a two-step process, similar to that of data classification. Although
for prediction, we do not utilize the phrasing of "class label attribute" because the attribute for
which values are being predicted is consistently valued (ordered) instead of categorical (district-
esteemed and unordered). The attribute can be referred to simply as the predicted attribute.
Prediction can be viewed as the construction and use of a model to assess the class of an unlabelled
object or to assess the value or value ranges of an attribute that a given object is likely to have.

4) Clustering: Clustering can be used to generate these labels. The objects are clustered based on the
principle of maximising the intra-class similarity and minimising the interclass similarity. That is,
clusters of objects are created so that objects inside a cluster have high similarity in contrast with
each other, but are different objects in other clusters. Each Cluster that is generated can be seen as a
class of objects, from which rules can be inferred.
5) Regression: Regression can be defined as a statistical modelling method in which previously
obtained data is used to predicting a continuous quantity for new observations. This classifier is
also known as the Continuous Value Classifier. There are two types of regression models: Linear
regression and multiple linear regression models.
6) Artificial Neural Network (ANN) Classifier Method: An Artificial neural network (ANN) also
referred to as simply a "Neural Network" (NN), could be a process model supported by biological
neural networks. It consists of an interconnected collection of artificial neurons. A neural network
is a set of connected input/ output units where each connection has a weight associated with it.
During the knowledge phase, the network acquires by adjusting the weights to be able to predict
the correct class label of the input samples.
An artificial neural network is an adjective system that changes its structure-supported
information that flows through the artificial network during a learning section. The ANN relies on
the principle of learning by example. There are two classical types of neural networks, perceptron
and also multilayer perceptron.

Shridevi Degree College , Tumkur Page 10

 Data Mining
7) Outlier Detection: A database may contain data objects that do not comply with the general
behaviour or model of the data. These data objects are Outliers. They investigation of OUTLIER
data is known as OUTLIER MINING. An outlier may be detected using statistical tests which
assume a distribution or probability model for the data.
8) Genetic Algorithm: Genetic algorithms are adaptive heuristic search algorithms that belong to the
larger part of evolutionary algorithms. Genetic algorithms are based on the ideas of natural
selection and genetics. These are intelligent exploitation of random search provided with historical
data to direct the search into the region of better performance in solution space.

Difference between Database and Data Mining

Database Data Mining

 The database is the organised collection of  Data mining is analysing data from
data most of the times, these raw data a different information to discover useful
stored in very large databases. knowledge.
 A database may contains different levels of  Data mining deals with extracting useful
abstraction in its architecture. and previously unknown information
from raw data.
 Typically the three levels :external  The data mining process relies on the
,conceptual and internal make up the data compiled in the data warehousing
database architecture. phase in order to detect
meaningful patterns.
KDD v/s Data Mining

Parameter KDD Data Mining

Definition KDD refers to process of identifying valid, Data mining refers to a process of extracting useful and
novel, potentially useful and ultimately valuable information or patterns from large data set.
understandable patterns and relationship
in data.
Objective To find useful knowledge from data. To extract useful information from data.

Technique Data cleaning, data integration, data Association rules, classification, clustering, regression,
used selection, data information, data mining, decision trees, neural networks, and dimensionality
pattern evaluation and knowledge reduction.
representation and visualisation.
Output Structured information, such as rules and Patterns, association, or insights that can be used to
models that can be used to make decision improve decision-making or Understanding.
or predictions.
Focus Focus is on the discovery of useful Data mining focus is on the discovery of patterns or
knowledge, rather than simply finding relationships in data.
patterns in data.
Role of Domain expertise is important in KDD, as Domain expertise is less critical in data mining, as the
domain it helps in defining the goals of the algorithms and design to identify patterns without
expertise process, choosing appropriate data, and relying on prior knowledge.
interpreting the results.

Shridevi Degree College , Tumkur Page 10

 Data Mining

Problems in Data Mining

1. Poor data quality such as noisy data, dirty data, missing values, inexact or incorrect values, inadequate
data size and poor representation in data sampling.
2. Integrating conflicting or redundant data from different sources and forms: multimedia files (audio,
video and images), geo data, text, social, numeric, etc...
3. Proliferation of security and privacy concerns by individuals, organisations and governments.
4. Unavailability of data or difficult access to data.
5. Efficiency and scalability of data mining algorithms to effectively extract the information from huge
amount of data in databases.
6. Dealing with huge datasets the required distributed approaches.
7. Dealing with non-static, unbalanced and cost-sensitive data.
8. Mining information from heterogeneous databases and global information systems.
9. Constant Updating of models to handle data velocity or new incoming data.
10. High cost of buying and maintaining powerful softwares, servers and storage hardware that handles
large amounts of data.
11. Processing of large, complex and unstructured data into a structured format.
12. Sheer Quantity of output from many data mining methods.

Data Mining Tools:

1. Rapid Miner: It is a Data science software that provides an integrated environment for data
preparation machine learning, deep learning, text mining and predictive Analysis.
 It is one of the open source system for data mining.
 The program is written entirely in Java programming language.
2. Oracle Data Mining: It is representation of Oracles advanced analytics Database. Market leading
companies use it to the maximum potential of their Data to make accurate predictions. This system
works with a powerful Data Algorithm to target best customers further it customizes customer
profiles in a disserved way.
3. IBMSPSS Modular: In this modular, text analysis and it’s state of heart visual interfaces proved to
be extremely valuable, it helps to generate Data mining algorithm with minimal/ No programming.
It can widely used in Neural Networks.
4. KNIME(Konstanz Information Minor): It is open source Data Analysis Platform in this you can
deploy, Scale and familiarize Data within less than no time.
5. OLTP(Online Transaction Processing System): The main focus of OLAP system is to record the
current updates, Insertion and Deletion while transaction. The OLAP queries are simple and short
and hence require less time in processing also require less space.

Advantages of Data Mining:-

 Better Decision-making: Data mining helps to extract useful information from large datasets,
which can be used to make informed and accurate decisions.
 Improved Marketing: Data mining can help businesses identify their target market and develop
effective marketing strategies. By analysing customer data, businesses can identify customer
preferences.
Page 11
 Data Mining

 Increased Efficiency: Data mining can help businesses streamline their operations by identifying
inefficiencies and areas for improvement,by analysing data on production processes, supply chains,
and employee performance.
 Fraud Detection: Data mining can be used to identify fraudulent activities in financial
transactions, insurance claims, and other areas, by analysing patterns and relationships in the data.
 Customer Retention: Data mining can help businesses identify customers who are at risk of
leaving and develop strategies to retain them, by analysing customer data.
 Competitive Advantage: Data mining can help businesses gain a competitive advantage by
identifying new opportunities and emerging trends, by analysing data on customer behaviour,
market trends, and competitor activity.
 Improved Healthcare: Data mining can be used to improve healthcare outcomes by analysing
patient data to identify patterns and relationships, by analysing medical records and other patient
data.

Disadvantages of Data Mining:

 Data Quality: Data mining relies heavily on the quality of the data used for analysis. If the data is
incomplete, inaccurate, or inconsistent, the results of the analysis may be unreliable.
 Data Privacy and Security: Data mining involves analysing large amounts of data, which may
include sensitive information about individuals or organisations. If this data falls into the wrong
hands, it could be used for malicious purposes, such as identity theft or corporate espionage.
 Ethical Considerations: Data mining raises ethical questions around privacy, surveillance, and
discrimination.
 Technical Complexity: Data mining requires expertise in various fields, including statistics,
computer science, and domain knowledge. The technical complexity of the process can be a barrier
to entry for some businesses and organisations.
 Cost: Data mining can be expensive, particularly if large datasets need to be analysed. This may be
a barrier to entry for small businesses and organisations
 Interpretation of Results: Data mining algorithms generate large amounts of data, which can be
difficult to interpret. It may be challenging for businesses and organisations to identify meaningful
patterns and relationships in the data.
 Dependence on Technology: Data mining relies heavily on technology, which can be a source of
risk. Technical failures, such as hardware or software crashes, can lead to data loss or corruption.

Page 12