-
Data mining is study of algorithms for finding patterns in large data sets. It is an integral part of modern industry, where data from its operations and customers are mined for gaining business insight. It is also important in modern scientific endeavors. Data mining is an interdisciplinary topic involving, databases, machine learning and algorithms. The course will cover the fundamentals of data mining. It will explain the basic algorithms like data preprocessing, association rules, classification, clustering, sequence mining and visualization. It will also explain implementations in open source software. Finally, case studies on industrial problems will be demonstrated.INTENDED AUDIENCE : Any engineering discipline and mathematics,Physics.PREREQUISITES :NilINDUSTRY SUPPORT : TCS,Infosys,CTS,Accenture
Overview
Syllabus
-
Week 1:Introduction, Data Preprocessing
Week 2:Association Rule Mining, Classification Basics
Week 3:Decision Tree, Bayes Classifier, K nearest neighbor
Week 4:Support Vector Machine, Kernel Machine
Week 5:Clustering, Outlier detection
Week 6:Sequence mining
Week 7:Evaluation, Visualization.
Week 8:Case studies
