Data Analytics Question

I uploaded the files which contains the Exercise and the other files to solve it.

Please adhere to the following:

1- Do not use artificial intelligence, as the university detects its use and has Turnitin.

2- Do not duplicate assignments from other students.

3- Submit within the specified timeframe; I have chosen 4 days.

Delivering Performance Excellence (DPE): Business Analytics

Business Analytics Assessment: Individual Assignment

Mark: 35% of DPE Module marks

Submission date: 5th March 2026

Required: Business Analytics Report

Format: 1500-2000 words (Excluding graphs and charts) based on the guidelines below.

I. Assignment Brief

This assignment requires you to produce an academically grounded business analytics report.

You are required to select one dataset from the pool of datasets provided on the assignment

Loop submission link. All datasets have been sourced from open-access repositories and are

approved for use for educational purposes only.

Choose a dataset that aligns with an industry sector of interest to you (e.g. Healthcare

Management, Human Resources, Marketing, Inventory Management, Transport, Education,

etc.). Your role is to identify a business problem or opportunity that can be addressed

analytically using the variables available in the selected dataset.

Your task is to conduct the appropriate analytics processes to address the identified problem or

opportunity and to present your findings in a business analytics report.

In brief, a business analytics report is a structured document that presents data-driven insights to

inform business decision-making. Using your chosen dataset, you are required to conduct descriptive,

predictive, and prescriptive analytics.

1. 2. II. Analytics Report Framework

1. Organisational Context and Decision Challenge (20%)

This section must demonstrate that the analytics work is grounded in a business need. You should

include:

Industry Context: Introduce the sector and explain the relevance of the dataset to a real

industry setting.

Decision Problem or Strategic Opportunity: Clearly define the business problem or

opportunity. Business Value and Strategic Importance: Explain why this issue matters and what

organisational value is sought (e.g., efficiency, growth, risk mitigation, optimisation).

Analytics Objectives and Key Questions: Frame clear, data-answerable business questions

aligned with the decision challenge.

2. Working with Data and Analytical Design (20%)

This section must demonstrate the use of the dataset to answer the business questions, not just

technical execution. You should include:

Dataset Overview and Variable Classification: Identify key predictors (independent variables)

and targets (dependent variables).

Data Exploration and Assumptions: Discuss patterns, outliers, and potential limitations.

Data Preparation and Transformation: Explain cleaning steps and justification.

Analytical Approach and Justification: Describe why specific descriptive, predictive, and

prescriptive techniques were selected (you can limit the techniques to those taught in class).

3. Analytical Execution and Evidence (30%)

This section presents the analytic process and techniques in a structured analytical output.

Descriptive steps and insights

Predictive modelling results

Prescriptive analysis and decision scenarios

Analytics Dashboard: All key charts, tables, and visualisations must be presented together.

Each visual must include a short managerial insight statement.

4. Critical Evaluation and Managerial Insight (20%)

This section discusses your evaluation of the results.

Interpretation of results

Discussion of reliability, assumptions, risks, and limitations.

Managerial implications

Demonstrate how analytical outputs are combined with your industry understanding to inform

decisions.

5. Recommendations and Decision Communication (5%)

This section translates your analysis into action.

Actionable recommendations

Expected organisational impact

Implementation considerations

6. Housekeeping (5%)

Harvard or APA referencing (include DOIs where available)

Logical structure and coherent argumentation

Table of contents

Professional presentation of dashboard and appendices

II. Minimum Requirements for Technical Analytics

1. Descriptive Analytics

a) Select four (4) variables from the dataset and formulate four (4) descriptive analytics

questions that are relevant to your stated business problem.

b) Produce data visualisations to support your descriptive analysis and summary statistics.c) Each visualisation must include a brief insight statement explaining what the visual shows

and what decision or action it may inform.

All descriptive analytics visualisations should be compiled and presented together in an

analytics dashboard.

2. Predictive Analytics

Formulate and analyse at least one (1) predictive analytics question. Explain how the results of the

analysis could influence or support the business decision or action.

3. Prescriptive Analytics

Formulate and analyse at least one (1) prescriptive analytics question. Clearly explain how the

resulting recommendation would change or improve the business decision or action.

Notes:

1. 2. 3. Academic work at MSc level is expected to demonstrate independent research and critical

judgement, supported by academic evidence and reputable third-party sources. Please use the

Harvard or APA referencing style throughout your work.

A wide range of relevant peer-reviewed journal articles covering all areas of analytics is

available and should be consulted where appropriate.

Plagiarism will not be tolerated. All sources must be properly acknowledged in accordance

with the chosen referencing style in short : This is not a data exercise.

It is a decision-focused business analytics report.

You are expected to:

Choose one dataset

Identify a real business problem or opportunity

Move through:

o Descriptive

o Predictive

o Prescriptive analytics

Translate everything into managerial decisions

Its 35% of the module. High stakes.

The structure is fixed. Marks are allocated per section.

1. Organisational Context & Decision Challenge (20%)

This is where most students go wrong.

You must:

Introduce the industry

Explain why the dataset is relevant

Define a clear business problem

Identify your target variable

Explain:

o Why this problem matters

o What decision will be made

o What business value is expected

Important:

Do NOT write data questions like:What is the average X?

Instead write: What factors influence X so that management can decide Y?

This section is strategic. Not technical.

Working with Data & Analytical Design (20%)

Now you move into:

Variable classification (dependent vs independent)

Data exploration (patterns, outliers, assumptions)

Data cleaning and justification

Why you selected:

o Descriptive methods

o Predictive model

o Prescriptive technique

Key rule:

Do not dump everything you tried in Excel.

Only include what supports your decision logic.

Analytical Execution & Evidence (30%)

This is your technical core.

Descriptive (Minimum Requirement)

4 variables

4 descriptive questions

Visualisations

Each visual must include a short managerial insight

Not just: Mean = 20

But:The high variance suggests instability in X, which may affect Y decision.

Predictive (Minimum 1)

One clear predictive question

One target variable

Regression (if continuous)

Logistic regression if categorical (be careful here)

Explain:

What does the model tell management?

What decisions does it support

Prescriptive (Minimum 1)

Use Solver or scenario analysis

Show how decision changes

Show improvement logic

This is about: Given what we know, what should we do?

Dashboard

All visuals must be presented together.

Each must include:

Clear label

Short managerial insight

No random graphs.

4. Critical Evaluation & Managerial Insight (20%)

This is where MSc-level thinking shows.

You must:

Interpret results in business terms

Discuss:

o Reliability

o Assumptions

o Risks

o Limitations

Show understanding beyond Excel

This is not repeating results.

This is critical reflection.

5. Recommendations (5%)

Clear.

Actionable.

Decision-focused.

Explain:

What should management do?

Expected impact

Implementation considerations

6. Housekeeping (5%)

15002000 words

Harvard or APA

Table of contents

Professional structure

Proper placement of figures (not dumped in appendix)

Minimum Technical Requirements (Non-Negotiable)

From the brief :

4 descriptive questions

1 predictive

1 prescriptive

Dashboard compiled

Each visual includes insight statement

If one of these is missing, marks drop immediately.

The Most Important Warnings from the Transcript

From your professors explanation :

You must define your own business problem.

Target variable choice is critical.

Keep regression constraints in mind.

Do not overwhelm with technical noise.

Business value > technical complexity.

Critical evaluation separates high grades from average ones.

Use DCU grade descriptor to aim for distinction level thinking

What I Need From You Now

To properly guide you:

1. Which dataset are you choosing?

2. What industry is it from?

3. Do you already have a business problem in mind?

4. Is your target variable continuous or categorical?

Once I know that, I can:

Help you refine your decision challenge

Make sure your target variable works for regression

Structure your descriptive questions correctly

Design your predictive + prescriptive logic properly

Make sure your report hits distinction level

THE PROFESSOR IMPORTANT REQUIREMENTS:

This Is a Decision Report Not a Data Report

She repeated this multiple times.

Your work must always answer:

What decision will this analysis support?

If your report sounds like:

We analysed X.

The mean is Y.

The correlation is Z.

Thats weak.

It must sound like:

Understanding X allows management to decide Y.

If variable A increases, the company should consider B.

Everything must point toward decision-making.

Target Variable Choice Is Critical

She warned clearly about this.

If your target variable is:

Categorical you cannot run linear regression.

Binary you would need logistic regression.

She explicitly mentioned students making this mistake and realising too late.

So before you start:

Confirm your target variable works with the regression method taught in class.

This is a technical constraint you must respect.

Do Not Overcrowd With Analytics

She said:

You will try many things in Excel.

Do NOT put everything in the report.

Only include analysis that supports your decision logic.

This means:

No random charts.

No unnecessary statistics.

No just because I can analysis.

Be selective. Strategic. Intentional.

Insight After Every Analysis

This was strongly emphasised.

For:

Every descriptive statistic

Every visual

Every model result

You must add 12 sentences explaining:

What does this mean?

Why does it matter?

What decision does it influence?

No raw outputs

Section 1 and Section 4 Require the Most Thinking

She clearly said:

Section 2 and 3 are more technical.

Section 1 (context) and Section 4 (critical evaluation) require real thinking.

These sections determine distinction-level work.

Especially Section 4:

Reliability

Assumptions

What you would improve

What data is missing

Risks of using this model

Thats where MSc depth shows.

Use Academic Support to Justify Importance

She suggested:

Read 12 peer-reviewed papers in your datasets area.

Use them to justify:

o Why your problem matters.

o Why certain variables are important.

o What might be missing.

This strengthens Section 1 and Section 4 significantly.

Many students skip this and lose quality.

Business Value Over Technical Complexity

She made this very clear.

Doing:

5 regressions

10 models

Complex analysis

Does NOT equal higher marks.

Clear logic + decision value = higher marks.

Dashboard Must Be Clean and Purposeful

She emphasised:

All visuals together.

Each must serve the business question.

No visual noise.

Each visual must have insight.

Dumping visuals into appendix is wrong.

Putting visuals randomly in text is wrong.

They must be placed logically and referenced properly.

This Is Structured Like a Research Paper

She compared it to:

Methodology

Results

Interpretation

Recommendations

That means:

Clear flow.

Logical progression.

Not jumping between sections.

Work Within Constraints

She said something very important conceptually:

Business analytics also means working within:

Data constraints

Technical constraints

Skill constraints

If something cannot be done with your dataset or tools,

acknowledge it and justify your approach.

That shows maturity.

The Real Hidden Message

What she really emphasised overall:

This assignment tests whether you can:

Think like a decision-maker

Think like an analyst

Connect technical outputs to business logic

Critically evaluate your own analysis

Not just use Excel.

WRITE MY PAPER