Business Analytics
Sep 2025 Examination
Q1. Given a business scenario where a company wants to integrate structured sales data
with unstructured customer feedback, explain how you would preprocess and combine
these data types for effective analytics. Illustrate your approach using real- world
examples. (10 Marks)
Ans 1.
Introduction
In today’s data-driven environment, businesses generate and collect vast amounts of data in
both structured and unstructured forms. Structured data refers to information organized in
tabular formats, such as sales data stored in relational databases, while unstructured data
includes free-text feedback from customers, reviews, and social media interactions. An
integrated analysis of these datasets offers deeper insights into customer behavior, product
performance, and sales effectiveness. For example, a company may want to correlate monthly
sales figures with customer sentiment from online reviews to understand why certain
products outperform others
Q2. Assess the impact of Type I and Type II errors in hypothesis testing within the
context of business analytics. Evaluate how the balance between these errors can affect
strategic business decisions, providing justification for the selection of significance
levels. (10 Marks)
Ans 2.
Introduction
Hypothesis testing is a cornerstone of statistical analysis in business analytics, used to make
data-driven decisions under uncertainty. However, this process is susceptible to two types of
errors—Type I and Type II—which can significantly influence business outcomes. A Type I
error occurs when a true null hypothesis is wrongly rejected, while a Type II error arises
when a false null hypothesis is wrongly accepted. The consequences of these errors vary
depending on the business context, such as launching a new product, implementing marketing
campaigns, or deciding on credit
Q3(A) Scenario: A real estate agent wants to predict the price of a house based on its
size in square feet. She collects data from 50 recent house sales in a particular
neighborhood, recording the size of each house and its corresponding sale price.
Question:
Using Simple Linear Regression, how can the real estate agent model the relationship
between house size and price?
- What would be the dependent and independent variables?
- How can she use this model to predict the price of a 2,000 sq. ft. house? (5 Marks)
Ans 3a.
Introduction
In real estate analytics, estimating house prices based on quantifiable features like size is a
common task. Simple Linear Regression is a statistical method that helps model the
relationship between a single independent variable and a dependent variable. In this case, a
real estate agent can analyze how house size in square feet impacts the sale price. By
applying linear regression to
Q3 (B) Scenario:
An HR analyst is trying to predict the monthly salary of employees in a tech company
based on multiple factors: years of experience, education level (in years), and number of
certifications. She gathers data from 100 employees.
Question:
Using Multiple Linear Regression, how can the analyst build a model to predict an
employee’s salary?
- Identify the dependent and independent variables.
- How can this model help in making compensation decisions for new hires with known
qualifications? (5 Marks)
Ans 3b.
Introduction
In the dynamic environment of human resource analytics, understanding how various factors
contribute to employee compensation is essential. Multiple Linear Regression is a statistical
method used when multiple independent variables influence a dependent variable. In this
scenario, an HR analyst seeks to predict the monthly salary of employees using inputs such as
years
