Business Question

Post ID: 3542186

Overview

Assignment Title:

Machine Learning for Customer Churn Prediction and Retention Decision-Making in GCC Telecommunications Companies

Objective: Prepare a complete MBA-level academic assignment that fully complies with all course requirements and targets the highest possible grade according to the assessment rubric.

General Requirements:

Individual assignment.
Word count between 2,000 and 3,000 words only.
Professional academic writing.
APA 7th Edition referencing.
Minimum 10 academic references.
Use recent academic journals, books, industry reports, and reputable business sources.
Proper in-text citations throughout the report.
Original work suitable for Turnitin submission.
Strong critical analysis rather than descriptive writing.
Professional formatting and structure.

Required Report Structure

Executive Summary (150–200 words)

Provide:

Overview of the business problem.
Selected machine learning approach.
Key findings.
Main recommendations.
Expected business value.

Section 1: Business Problem and Decision Context

1.1 Organisation Background
Include:

Telecommunications industry overview.
GCC telecommunications market.
Services offered by telecom companies.
Market environment and competition.

1.2 Business Problem
Discuss:

Customer churn challenges.
Increasing customer acquisition costs.
Impact on profitability.
Need for improved customer retention decisions.

1.3 Decision-Making Context
Identify and explain:

Strategic decisions.
Tactical decisions.
Operational decisions.

Clearly explain: Which customers should receive retention interventions and why.

Section 2: Role of Machine Learning in Business Decision-Making

2.1 Machine Learning Overview
Define:

Artificial Intelligence (AI).
Machine Learning (ML).
Predictive Analytics.

2.2 Types of Machine Learning

Explain:

Supervised Learning.
Unsupervised Learning.
Reinforcement Learning.

Provide business examples for each type.

2.3 Selected Machine Learning Approach

Justify why Supervised Learning is the most suitable approach for customer churn prediction.

Section 3: Data Requirements and Preparation

Identify the data required for churn prediction.

Suggested Variables:

Customer Age.
Gender.
Monthly Charges.
Contract Type.
Customer Tenure.
Internet Usage.
Customer Complaints.
Payment Method.
Customer Satisfaction Score.
Service Plan.
Churn Status.

Discuss:

Data collection.
Data cleaning.
Missing values treatment.
Data preparation.
Feature selection.

Section 4: Machine Learning Model Selection and Application

Primary Model:
Decision Tree Classification.

Secondary Model:
Random Forest Classification.

For each model explain:

Why it was selected.
How it works in simple business language.
Input variables.
Output results.
Strengths and limitations.

Decision Support Application

Explain how managers can use model outputs to:

Predict churn probability.
Prioritise retention efforts.
Allocate marketing budgets.
Improve customer service interventions.

Section 5: Business Impact, Ethical Issues and Risks

5.1 Business Benefits

Discuss at least five benefits:

Improved decision quality.
Reduced uncertainty.
Better customer retention.
Cost savings.
Revenue growth.
Competitive advantage.
Improved customer satisfaction.

5.2 Risks and Challenges

Discuss:

Data privacy concerns.
Algorithmic bias.
Poor data quality.
Cybersecurity threats.
High implementation costs.
Lack of analytical expertise.

5.3 Ethical Considerations

Discuss:

Fairness.
Transparency.
Accountability.
Responsible AI.
Data protection.

Include examples from GCC organisations where possible.

Section 6: Recommendations and Conclusion

Recommendations

Provide at least five practical recommendations:

Establish strong data governance policies.
Improve customer data quality.
Continuously monitor model performance.
Train staff on analytics and AI tools.
Implement ethical AI governance practices.
Develop targeted retention campaigns.
Conduct periodic model reviews.

Conclusion

Summarise:

Business problem.
Machine learning solution.
Expected business value.
Decision-making improvements.
Strategic importance of predictive analytics.

References

Requirements:

Minimum 10 academic references.
APA 7th Edition format.
Recent and credible sources.

Appendices

Include only if required.

Presentation Requirements

In addition to the report, prepare a professional executive presentation.

Requirements:

Maximum 15 slides only.
Executive-level design.
MBA-level professional appearance.
Clean visual layout.
High-quality charts and graphics.
Minimal text.
Suitable for a 10–15 minute presentation.