(SEM VI) THEORY EXAMINATION 2024-25 DATA ANALYTICS

Data Analytics (BADS601)

Section-Wise Important Questions & Study Notes

SECTION–A

(Attempt ALL | 2 × 7 = 14)
Write short, crisp answers (2–3 lines). Focus on definitions + examples.

(a) Big Data & Real-World Examples

Big Data refers to extremely large, fast-growing, and complex datasets characterized by Volume, Velocity, Variety, Veracity, and Value.
Examples: social media data (Facebook, Twitter), sensor/IoT data, e-commerce transactions, healthcare records.

(b) Analysis vs Reporting

Analysis: discovering patterns, insights, and predictions from data.

Reporting: presenting summarized historical data in charts, tables, and dashboards.

(c) Need of Outlier Removal in Regression

Outliers can distort regression coefficients, reduce model accuracy, and lead to misleading predictions; removing them improves reliability.

(d) Multivariate Analysis

Statistical analysis involving more than two variables to understand relationships and patterns (e.g., PCA, factor analysis).

(e) Sampling Data in a Stream

Techniques include random sampling, reservoir sampling, sliding window sampling, used when data arrives continuously.

(f) CLIQUE & High-Dimensional Clustering

CLIQUE is a grid-based clustering algorithm designed for high-dimensional data by identifying dense subspaces.

(g) Popular Data Visualization Tools

Tableau, Power BI, Matplotlib, Seaborn, ggplot2, Excel, and D3.js.

SECTION–B

(Attempt any THREE | 7 × 3 = 21)
Write descriptive answers with headings and diagrams.

(a) Stages in Big Data Lifecycle

Data generation                                             Data acquisition

Data storage                                                   Data processing

Data analysis                                                   Data visualization

Decision making

(b) Utility of Neural Networks in Analytics

Neural networks help in classification, prediction, pattern recognition, image processing, speech recognition, and fraud detection.

(c) Steps in Query Processing                       Parsing & validation

Query optimization                                      Query execution

Result generation

(d) Mining Frequent Itemsets Using FP-Tree

FP-Tree compresses transaction data without candidate generation.
Steps:                                                            Build FP-Tree

Generate conditional FP-Trees                      Extract frequent itemsets

(e) NoSQL vs RDBMS

SECTION–C

(Attempt any ONE | 7 × 1 = 7)

(a) Data Preparation Stage (Most Time-Consuming)

Includes data cleaning, handling missing values, normalization, transformation, integration, and feature selection.
It is time-consuming because real-world data is incomplete, inconsistent, and noisy.

OR

(b) Importance of Data Analytics in Business

Better decision making                                                                  Cost optimization                               Customer behavior analysis                                                           Competitive advantage