DATA ANALYTICS [MODEL PAPER]

SECTION – A

 What is Big Data?

Big data refers to extremely large, fast-growing, and complex sets of data that traditional
data-processing tools can’t handle [Link] is usesd to analyze patterns, trends, and
relationships that help organizations make better decisions, improve efficiency, and predict
outcomes.

 What is Deep Learning?

Deep Learning is a subset of Machine Learning that uses multi-layered artificial neural
networks to automatically learn patterns and representations from large amounts of data,
especially for tasks like image recognition, speech recognition, and natural language
processing.

 Give the formula for calculating probable error?

Where:
 𝑟 is the calculated coefficient of correlation.
 𝑛 is the number of pairs of observations or the sample size.
 0.6745 is a constant derived from the normal distribution, representing the
range around the mean within which 50% of the values are expected to fall (it
is approximately two-thirds of the standard error).

 Write the two Regression Equations?

  What is M-Language?
M-Language is a functional programming language used in Power BI and Power Query to
perform data extraction, transformation, and loading (ETL). It helps in cleaning, shaping, and
preparing data from various sources for analysis.

 Write any two benefits of Case Studies?

 They provide an in-depth understanding of real-world problems.
 They help in analyzing complex situations in a practical context.
 They support better decision-making through detailed evidence.
 They enhance learning by linking theory with practical application.

SECTION – B

 Explain the key features of Data Analytics.

Key Features of Data Analytics:

 Data Collection:
Data analytics involves gathering data from multiple sources such as databases,
sensors, websites, and surveys.
 Data Cleaning and Preparation:
Raw data is processed to remove errors, inconsistencies, and missing values to ensure
accuracy.
 Data Processing:
Large volumes of data are processed efficiently using analytical tools and techniques.
 Data Analysis:
Statistical, mathematical, and computational methods are applied to identify patterns,
trends, and relationships in data.
 Data Visualization:
Insights are presented using charts, graphs, and dashboards for easy understanding.
 Decision Support:
Data analytics helps organizations make informed and data-driven decisions.
 Predictive and Prescriptive Insights:
It enables forecasting future trends and suggesting optimal actions

8. Discuss the key challenges in Data Analytics.

 Data Quality Issues:
Incomplete, inconsistent, or inaccurate data can lead to incorrect analysis and
misleading results.
  Data Integration:
Combining data from multiple sources and formats is complex and time-consuming.
 Large Volume of Data:
Handling and processing huge amounts of data (Big Data) requires powerful tools and
infrastructure.
 Data Security and Privacy:
Protecting sensitive data and complying with legal and ethical regulations is a major
challenge.
 Lack of Skilled Professionals:
There is often a shortage of trained data analysts and data scientists.
 Data Interpretation:
Converting analytical results into meaningful insights for decision-making can be
difficult.
 Rapidly Changing Technology:
Keeping up with new tools, platforms, and techniques in data analytics is challenging.

9. Find the probability of getting a sum of 9 where two fair dice

are thrown.
When two fair dice are thrown,

each die has 6 faces numbered from 1 to 6.

Step 1: Total number of possible outcomes

Each die can show 6 outcomes, so the total number of outcomes is:

6×6=366

Step 2: Outcomes that give a sum of 9

List all possible pairs whose sum is 9:

 (3,6) (3,6) (3,6)

 (4,5) (4,5) (4,5)
 (5,4) (5,4) (5,4)
 (6,3) (6,3) (6,3)

So, the number of favorable outcomes = 4.

 10. A fair cion and a fair die is throw. Find the probabilities of

i. Head on the coin and the number 6 on the die.

ii. Head on the coin and even number on the die.
We have:

 A fair coin (2 outcomes: Head (H) or Tail (T))

 A fair die (6 outcomes: 1, 2, 3, 4, 5, 6)

The total number of possible outcomes when we throw both together is: 2×6=122

i. Probability of Head on the coin and number 6 on the die

 Number of favorable outcomes: only (H,6) → 1 outcome

 Total outcomes: 12
1
P(H and 6) = 12

ii. Probability of Head on the coin and even number on the die

 Even numbers on a die: 2, 4, 6 → 3 outcomes

 Each of these can occur with Head: (H,2), (H,4), (H,6) → 3 favorable outcomes
 Total outcomes: 12
3 1
P(H and even) = =
12 4

11. Explain the different variants of Power BI.

Power BI is Microsoft’s suite of business analytics tools that allow users to visualize data and share
insights. There are several variants depending on the user scenario: Desktop, Service, Mobile,
Report Server, and Premium.

1. Power BI Desktop

 Type: Free Windows application

 Purpose: Create reports and dashboards
 Key Features:
o Connect to multiple data sources (Excel, SQL, web, etc.)
o Transform and model data using Power Query and DAX
o Build interactive visualizations and reports
 Best For: Individual report authors and data analysts
 Cost: Free

2. Power BI Service (Power BI Online / [Link])

 Type: Cloud-based platform

 Purpose: Publish, share, and collaborate on reports
 Key Features:
o Share dashboards with colleagues
o Schedule data refreshes
o Workspaces for team collaboration
o Real-time dashboards
 Best For: Teams and organizations who need online access to reports
 Cost: Free (with limited sharing) or Pro license ($10/user/month) for collaboration

3. Power BI Mobile

 Type: Mobile application (iOS, Android, Windows)

 Purpose: Access dashboards and reports on mobile devices
 Key Features:
o Receive notifications for data alerts
o Interactive visuals on the go
o Offline access for previously viewed reports
 Best For: Managers and executives who need insights anywhere

4. Power BI Report Server

 Type: On-premises server

 Purpose: Host and manage Power BI reports on your own servers
 Key Features:
o Store reports locally instead of in the cloud
o Schedule data refreshes
o Support for paginated reports (like SQL Server Reporting Services)
 Best For: Organizations with strict data compliance or no cloud access
 Cost: Requires Power BI Premium license

5. Power BI Premium
  Type: Licensing model for enterprises
 Purpose: High-scale analytics for large organizations
 Key Features:
o Dedicated cloud capacity for faster performance
o Larger data volumes (up to 400 GB datasets in Premium per dataset)
o Paginated reports
o AI-powered features
o Advanced governance and administration
 Best For: Large organizations needing enterprise-scale reporting
 Cost: Starts at $4,995 per month for capacity-based licensing

12. Explain the types of Case Study with Examples.

A case study is a detailed examination of a person, group, event, or situation to understand
underlying principles or outcomes. There are several types of case studies, usually
categorized based on their purpose or method.

1. Exploratory (or Pilot) Case Study

 Purpose: To explore a problem or situation when there is little existing knowledge.

 Focus: Identifying research questions, hypotheses, or variables for further study.
 Example:
o A company launches a small pilot project to see how remote work affects
productivity.
o A researcher studies the initial adoption of a new technology in a local school
before a larger study.

2. Descriptive Case Study

 Purpose: To describe a phenomenon in detail.

 Focus: Provides a detailed account of events, processes, or situations.
 Example:
o A report describing how Starbucks maintains customer loyalty through its
brand experience.
o A case study of a hospital documenting the workflow of patient care in the
emergency department.

3. Explanatory (or Causal) Case Study

 Purpose: To explain the cause-and-effect relationships.

 Focus: Understand why something happened and identify underlying causes.
 Example:
o Investigating why a specific product failed in the market.
 o Studying the reasons behind a decline in employee productivity after
organizational restructuring.

4. Intrinsic Case Study

 Purpose: To understand a unique or interesting case.

 Focus: The case itself is of primary interest, not generalization.
 Example:
o Examining the turnaround story of a unique startup that became successful
against all odds.
o Studying an individual patient with a rare medical condition.

5. Instrumental Case Study

 Purpose: To gain broader insights into a general phenomenon.

 Focus: The case is a tool to understand something beyond the specific case.
 Example:
o Analyzing the success of a particular school’s teaching method to understand
effective education strategies.
o Studying one company’s marketing strategy to draw lessons for the whole
industry.

6. Collective (or Multiple) Case Study

 Purpose: To study multiple cases together to understand a broader phenomenon.

 Focus: Comparison across cases to identify patterns.
 Example:
o Studying 10 tech startups to identify common factors in startup success.
o Comparing the responses of different cities to a public health crisis.

SECTION – C

13. Explain the process of web Analytics.

Web analytics is the process of collecting, measuring, analyzing, and reporting data from
a website to understand how users interact with it and how to improve performance.

Process of Web Analytics

1. Define Goals

 What it is: Decide what you want to achieve with your website.
 Example: Increase online sales, get more newsletter sign-ups, or improve user
engagement.
2. Collect Data

 What it is: Gather information about visitors and their behavior on the website.
 How: Use tools like Google Analytics, Adobe Analytics, or Matomo.
 Example: Number of visitors, pages viewed, time spent on site, clicks.

3. Measure Metrics

 What it is: Identify key metrics that show how well the website is performing.
 Common Metrics:
o Traffic: How many people visit your site
o Bounce Rate: How many leave after visiting one page
o Conversion Rate: How many complete a desired action (buy, sign-up)
o Average Session Duration: How long users stay

4. Analyze Data

 What it is: Study the data to understand user behavior and patterns.
 Example:
o Which pages are most popular?
o Which sources bring the most visitors?
o Why are people leaving the site quickly?

5. Report & Visualize

 What it is: Present insights in an understandable format like dashboards, charts, or

reports.
 Example:
o Show monthly website traffic trends
o Highlight which marketing campaigns are most effective

6. Take Action / Optimize

 What it is: Use insights to make improvements and test changes.

 Example:
o Improve website layout for easier navigation
o Run A/B tests on call-to-action buttons
o Adjust marketing campaigns based on visitor data

Summary Flow of Web Analytics Process

1. Define Goals → Decide what you want to achieve

2. Collect Data → Track visitor activity on your site
3. Measure Metrics → Identify key performance indicators (KPIs)
4. Analyze Data → Find patterns and insights
5. Report & Visualize → Present results in charts or dashboards
6. Take Action / Optimize → Improve website and test changes
14. If A and B are two events and P (B) ≠ 1 prove that
𝑃(𝐴)−𝑃(𝐴∩𝐵)
P(A| B) = Hence prove P(A∩ 𝐵)≥P(A)+P(B)-1.
1−𝑃(𝐵)
 15. From the following table find the correlation co-efficient
between age and percentage of players of students.

Age (in years) 16 17 18 19 20

Percentage of 70 50 40 30 10
players
The given data is :
Age (x) % Players (y)
16 70
17 50
18 40
19 30
20 10
 16. A survey was conducted to study the relationship between
Sales [X] and Advertisement [Y] abd the following results were
obtained.

Sales (rupees in Advertisement (rupees

crores) in lakhs)
Mean 115 120
S.D 10 15

i. Calculate the two regression equations.

ii. Find the likely sales when advertisement is rupees 100 lakhs.
iii. Find the likely advertisement when sales is rupees 150 crores.
Given :

Particulars Sales[X] Advertisement[Y]

Mean 115 120

S.D 10 15
 17. Explain the Visualization Elements in Power BI.
In Power BI, visualization elements are the components you use to represent data
visually—like charts, graphs, maps, and tables. They help users understand patterns,
trends, and insights quickly.

Key Visualization Elements in Power BI

1. Charts

Charts are used to display numeric data visually. Common types:

 Column/Bar Chart: Compare categories (e.g., sales by region)

 Line Chart: Show trends over time (e.g., revenue growth)
 Area Chart: Highlight cumulative trends
 Combo Chart: Combine column and line charts for comparison

2. Cards and KPIs

  Card: Displays a single value (e.g., total sales, total users)
 KPI (Key Performance Indicator): Shows performance against a target with color
indicators

3. Tables and Matrices

 Table: Displays data in rows and columns, like Excel

 Matrix: Like a pivot table, can show categories in rows and columns

4. Maps

Visualize geographical data:

 Map: Plot data points on a map

 Filled Map: Show regions filled with colors based on value

5. Slicers

 Slicers are interactive filters for dashboards.

 Example: Filter sales data by region, product, or date

6. Funnel and Gauge

 Funnel Chart: Shows stages in a process (e.g., sales pipeline)

 Gauge: Displays progress toward a goal (like a speedometer)

7. Tooltips

 Tooltips show additional information when you hover over a visual

 Example: Hover over a bar in a chart to see details about sales

8. Custom Visuals

 Power BI allows you to import custom visuals from the marketplace for specialized
needs

18. Write a Case Study on how Amazon utilizes business

analytics in its supply chain management.

Case Study: How Amazon Utilizes Business Analytics in Supply

Chain Management
Introduction

Amazon, one of the world’s largest e-commerce companies, has transformed online shopping
through efficient supply chain management. A key factor in its success is business
analytics, which helps Amazon make data-driven decisions, optimize operations, and
deliver products faster to customers.

Business Challenge

Amazon deals with millions of products, warehouses, and deliveries daily. The challenges
include:

 Predicting customer demand accurately

 Optimizing inventory and reducing storage costs
 Ensuring fast delivery to maintain customer satisfaction
 Managing returns efficiently

Use of Business Analytics

1. Demand Forecasting
o Amazon uses predictive analytics to forecast demand for each product in
every region.
o Algorithms analyze historical sales, seasonal trends, customer browsing data,
and even local events.
o This ensures products are stocked in the right warehouse before orders are
placed.
2. Inventory Optimization
o Analytics helps Amazon decide how much inventory to keep at each
fulfillment center.
o By using real-time data, Amazon minimizes overstocking and stockouts.
o Example: If a product is trending in New York, more stock is sent to nearby
warehouses.
3. Route Optimization
o Logistics analytics helps optimize delivery routes for speed and cost
efficiency.
o Amazon’s algorithms consider traffic patterns, weather, and delivery urgency.
o This is part of Amazon’s last-mile delivery strategy, ensuring same-day or
next-day delivery.
4. Supplier and Vendor Analytics
o Amazon monitors supplier performance using analytics to ensure timely
shipments and quality.
o This data helps in negotiating contracts and selecting reliable suppliers.
5. Returns Management
o Analytics identifies patterns in returns, helping Amazon predict and reduce
future returns.
o Example: Detecting defective product batches or sizing issues in clothing.

Impact of Analytics on Supply Chain

 Faster delivery times (same-day or next-day delivery for millions of products)

 Lower inventory costs due to better stock planning
 Higher customer satisfaction through accurate order fulfillment
 Data-driven decisions for continuous supply chain improvement
Conclusion

Amazon’s effective use of business analytics in its supply chain is a major reason for its
dominance in e-commerce. From demand forecasting to delivery optimization, analytics
allows Amazon to operate efficiently at a massive scale while maintaining excellent customer
service.