Department of Computer Science and Engineering The LNMIIT, Jaipur
CSE4011/CSE6031/CSE7011: Data Mining
Programme: M. Tech. (CSE) Year: 1 Semester: 1
Course: Program Elective Credits: 3 Hours: 40
Course Context and Overview:
The quantity of data, of varying types, is increasing at a phenomenal rate and it is necessary to
identify patterns that are interesting out of this data. Generally, Data Mining is the process of
analyzing data from different perspectives and summarizing it into useful information. It covers
algorithms and computational paradigms to find patterns, regularities (irregularities) in data,
perform prediction, and forecasting. This course will cover these concepts and techniques and
will illustrate the whole process by taking different case studies.
Prerequisite Courses: NIL
Course Outcomes (COs):
On completion of this course, the students will have the ability to:
CO1: Assess raw input data and process it to provide suitable input for a range of data mining
algorithms.
CO2: Apply, evaluate and analyze data mining algorithms and report the output appropriately.
CO3: Evaluate and implement a wide range of emerging and newly adopted methodologies and
technologies to facilitate knowledge discovery.
Course Topics:
Lecture
Contents
Hours
UNIT 1
Introduction
Introduction to Data Mining, Introduction to Major Building Blocks – Association 2
Pattern Mining, Classification, Clustering, Outlier Detection;
UNIT 2
Data Preparation
Types of Attributes, Feature Extraction, Creation, and Selection, Data Cleaning, 3
Dimensionality Reduction
Department of Computer Science and Engineering The LNMIIT, Jaipur
UNIT 3
Classification
Decision Trees (ID3 or C4.5 or J48): Attribute test Conditions, Best split, handling 4
continuous attributes, Training and Testing Error, MDL, Cost-sensitive learning,
Evaluating Performance of classifier.
Rule-based Classifiers (RIPPER): Rule ordering, Direct and Indirect Method of rule 2
Extraction, Rule Evaluation.
Statistical Classifier (Naïve Bayes): Estimating conditional probability and M- 4
estimate of conditional Probability, Bayes error rate.
Method of Comparing classifiers, Ensemble methods (Bagging, Boosting etc), 2
Multi-class Problem, One-class Classification 1
UNIT 4
Association Pattern Mining
Market basket Analysis 0.5
Frequent Itemset Mining Algorithms (Apriori) Maximal and Closed Frequent Itemsets, 4
Pattern Querying, Rule Generation, Evaluation of Association Pattern
Skewed Support Distribution 0.5
Continuous and categorical Attributes 1
Sequential Pattern Discovery 2.5
Subgraph Pattern Mining 2.5
Infrequent Patterns, Negative Patterns 2
UNIT 5
Clustering
Different types of Clustering and Clusters, Representative-based Clustering, Density- 3
based Clustering
Cluster Evaluation 1
Graph-based Clustering, Clustering using mixture Model, Clustering Categorical Data 3
Scalable Data Clustering 1
UNIT 6
Outlier Analysis
Statistical Approaches, Clustering-based Methods 1
Department of Computer Science and Engineering The LNMIIT, Jaipur
Textbook references:
Text Books:
1. P. Tan, M. Steinbach, V. Kumar: “Introduction to Data Mining,” Pearson Education,
2006
Reference books:
1. Charu C. Aggarwal, “Data Mining,” Springer, 2015
2. K. Pujari: “Data Mining Techniques,” Universities Press, 3rd Edition, 2013
3. J. Han, M. Kamber, “Data Mining: Concepts and Techniques”, Morgan Kaufmann
Publishers, Second Edition, 2006
4. M.J. Zaki & W. Meira Jr.: “Data Mining and Analysis – Fundamental Concepts and
Algorithms,” Cambridge University Press, 2014
Prepared By: Preety Singh, Bharavi Mishra
Last Modification: 7th July 2020
