course structure - DSpace at CUSAT

E15 - Data Mining
(July 2008)
Prerequisite: E3 - Applied Probability and Statistics
Unit 1
An overview of data mining: Data Mining: applications, Knowledge discovery,
Challenges, Data mining tasks, Examples.
Data: Different types of data, Quality of data, Data preprocessing methods. Measures of
similarity and dissimilarity of data.
Unit 2
The Iris data sets, Summary statistics, Visualization: Motivations, General concepts,
Techniques of visualization, Visualizing higher dimensional data, Overview of OLAP
and multidimensional data analysis.
Unit 3
Basic concepts of classification: Definition, Descriptive and Predictive modeling,
General approach to solving a classification problem, Decision Trees, Model overfitting
Evaluating the performance of a classifier, Methods for Comparing classifiers.
Alternative Techniques Of Classification: Rule based classifier, Nearest
neighbor classifiers, Baysiean classifiers, Artificial neural networks.
Unit 4
Association analysis: Basic concepts: Problem Definition ,Frequent Item set generation,
Rule generation, compact item sets, Alternative methods for generating frequent item
sets. Evaluation of association patterns.
Unit 5
Cluster analysis: Basic concepts And algorithms: K means, Agglomerative hierarchical
clustering, DBSCAN, Cluster evaluation .
Basics Of anomaly detection: Preliminaries, Statistical approaches.
Text Book:
Pang-Ning Tan, Michael Steinbach, Vipin Kumar, ‘Introduction to Data Mining’,
Pearson, 2006 .
References:
1 Ian H. Witten, Eibe Frank, ‘Data Mining: Practical Machine Learning Tools
and Techniques’, 2 nd Ed., Morgan Kaufmann, 2005.
2 Arun K. Pujari, ‘Data Mining Techniques’, Universities Press, 2006.
******