DATA WAREHOUSING & MINING
BSBC501
Objective: The objective of this course is to get students familiar with the data mining techniques, softwares and tools being used in Industries.
Expected Outcome: After completing this course, students will learn various tools and techniques which are prominent from Industrial point of view.
Instructions for Paper-Setter: The question paper will consist of FIve sectionsA, B, C, D and E. SectionA, B, C and D will have two questions from the respective sections of the syllabus and will carry 10 marks each. Section E will have 10 short answer type conceptual questions, which will cover the entire syllabus uniformly and will carry20 marks in all.
Instructions for Candidates: Candidates are required to attempt one question each from Sections A, B, C and D of the question paper and the entirE Section E.
Use of non-programmable scientific calculator is allowed.
Internal Assessment-40Marks
External Assessment-60Marks
SECTION-A
Introduction to Data Warehousing, The need for data warehousing, Operational & Informational Data Stores, Data Warehouse Characteristics, Data Warehouse role & Structure, The cost of warehousing data. Introduction to OLAP & OLTP, Difference between OLAP & OLTP. OLAP Operations.
SECTION-B
Building a DataWarehouse, Design/Technical/Implementation Considerations, Data Pre- processing Overview. Data Summarization, Data Cleaning, Data Transformation, Concept Hierarchy, Structure. Patterns & Models, Artificial Intelligence (Overview).
Multi dimensional Data Model, Schemas for Multidimensional Data (StarSchema, Snowflake Schema, Fact Constellation), DataWarehouse Architecture, DataWarehouse Design, OLAP.
Three-tier Architecture, Indexing & Querying in OLAP, OLAM, Efficient Methods of Cube Computation, Discovery Driven Exploration of Data Cubes, Attributed-Oriented Induction.
SECTION -C
Association Rule Mining, Market Basket Analysis, Apriori Algorithm, Mining Multilevel Association Rules, From Association Mining to Correlation Analysis, Constraint Based Association Mining, Introduction to Classification, Classification by decision Tree, Attribute Selection Measure.
SECTION -D
Introduction to Prediction techniques, Accuracy of a Classifier, Cross-Validation, Bootstrap, Boosting, Bagging, Introduction to Clustering, Classification of Various Clustering Algorithms, Selecting and Using Right DM Technique, Selecting and Using Right DM Technique, Data Visualization.
SuggestedBooks:
1. DataWarehousing, DataMining and OLAP : Alex Berson, First Edition, TataMcGraw Hill
2. Data Mining Concepts & Techniques, Jiawei Han & Micheline Kamber, Second Edition, Morgan Kaufmann Publishers
3. Modern Data Warehousing, Mining & Visualization Core Concepts, George M Marakas, First Edition, Pearson Education
4. Data Ware housing, Architecture & Implementation, Hawkin, PrenticeHall
5. DataMining: Modelling Data for Marketing, Risk and Customer Relationship Mgmt, Rud,Olivia, Paperback Edition
6. Data Mining Techniques, Berry, Michael, Third Edition
7. Data Mining, Data Ware housing and OLAP, Sharma, Gajendra, Second Edition
8. Data Mining with Case Studies, Gupta G K, Second Edition
9. Principles of Data Mining, Hand, David
