(SEM VI) THEORY EXAMINATION 2018-19 DATA WAREHOUSING AND DATA MINING

SECTION A – Conceptual Basics (Short Answers)

Section A tests the fundamental understanding of Data Warehousing and Data Mining concepts. Each question is short and direct, so answers should be precise, definition-focused, and to the point.

This section mainly covers:
 

The basic meaning and purpose of Data Mining

Core concepts like classification, association rules, and data generalization

The importance of data preprocessing before mining

Fundamental ideas such as data compression, backup, and recovery

Students are expected to:

Write clear definitions

Use simple examples where required

Avoid lengthy explanations

This section checks whether the student understands core terminology used throughout the subject.

SECTION B – Descriptive & Comparative Questions

Section B focuses on detailed explanations and comparisons. Questions here require concept clarity, structured answers, and logical flow.
 

Major areas tested in this section include:

Data cleaning and its different phases

Clustering requirements in data mining

Comparison between STAR schema and Snowflake schema

Concepts like aggregation, historical data, and query facilities

Data warehousing along with its advantages and disadvantages

To score well in this section:
 

Answers should be well-explained, not just definitions

Use headings or step-wise explanation

Comparisons should be written in a clear contrast format

Real-world or practical relevance should be highlighted wherever possible

This section evaluates the student’s depth of understanding and ability to explain concepts properly.

SECTION C – Analytical & Application-Based Questions

Section C is designed to test analytical thinking and application of concepts. Questions are more focused and require logical explanation or numerical analysis.
 

This section includes:
 

ETL process: data integration, transformation, and loading

Data reduction techniques and strategies

Numerical problems (mean, variance, standard deviation)

Comparative study of clustering algorithms like CURE vs CHAMELEON

Density-based and Grid-based clustering

Differences between OLTP and OLAP

Data warehouse architectures

Web mining and its types

Comparison of ROLAP and MOLAP

To answer effectively:

Numerical problems must show proper steps

Theory answers should include examples or diagrams (if possible)

Comparisons should clearly explain why one approach differs from another

This section checks whether students can apply theoretical knowledge to solve problems and explain advanced concepts.