OnlineNursingOwl
← All nursing posts

Business & Finance · Studypool

MGT632 – Machine Learning Applications in Business - Project

Post ID: 3542183

Complete Project Brief

Project Team

  1. Abdulelah Nabel Alarfaj
  2. Abdullah Alansari
  3. Yazeed Albalawi

Selected Project Topic

Customer Churn Prediction for Telecom Companies in GCC Using Machine Learning Techniques

Project Objective

Develop and evaluate machine learning models to predict customer churn in GCC telecom companies and provide business recommendations to improve customer retention and reduce customer loss.

Research Questions

  1. What factors influence customer churn in telecom companies?
  2. Which machine learning model provides the highest prediction accuracy?
  3. How can telecom companies reduce churn based on model findings?
Project Requirements

Report Requirements

  • Word Count: 3,000–4,000 words.
  • Academic Writing Style.
  • APA 7th Edition Referencing.
  • Minimum 10 academic references (journal articles, books, industry reports, and reputable business sources).
  • Turnitin Similarity: 15% or less.
  • AI Similarity: Less than 20%.
  • Professional formatting and structure.
  • All figures and tables must be properly cited.
Required Report Structure

Section 1: Introduction

Include:

  • Background of customer churn in telecom industry.
  • GCC telecom market overview.
  • Importance of churn prediction.
  • Project objectives.
  • Research questions.

Section 2: Literature Review

Include:

  • Review of previous studies on customer churn prediction.
  • Machine learning applications in customer retention.
  • Comparison of methodologies.
  • Research gap identification.
  • Recent studies from 2021–2026 where possible.

Section 3: Dataset Description

Include:

  • Dataset source.
  • Dataset characteristics.
  • Number of observations.
  • Variables and descriptions.
  • Data cleaning process.
  • Missing values handling.
  • Data preparation process.

Suggested Dataset: Telecom Customer Churn Dataset from Kaggle or IBM Customer Churn Dataset.

Section 4: Machine Learning Application

Apply and compare at least TWO machine learning models:

Model 1:

Model 2:

  • Random Forest

Optional additional model:

  • XGBoost

For each model include:

  • Methodology
  • Training process
  • Feature selection
  • Model parameters

Section 5: Model Evaluation

Evaluate using:

  • Accuracy
  • Precision
  • Recall
  • F1 Score
  • Confusion Matrix

Compare results between models and identify the best-performing model.

Section 6: Business Insights and Recommendations

Business Findings:

  • Key churn drivers.
  • Customer behavior patterns.
  • High-risk customer groups.

Recommendations:

  • Customer retention programs.
  • Loyalty initiatives.
  • Targeted marketing campaigns.
  • Service improvement actions.

Recommendations must be realistic, practical, and actionable.

Section 7: Conclusion

Include:

  • Project summary.
  • Main findings.
  • Limitations.
  • Future improvements.
Presentation Requirements

Create a professional presentation (15 minutes maximum).

Recommended Slides:

  1. Title Slide
  2. Project Overview
  3. Business Problem
  4. Objectives and Research Questions
  5. Literature Review Summary
  6. Dataset Overview
  7. Data Preparation
  8. Model 1 (Logistic Regression)
  9. Model 2 (Random Forest)
  10. Model Comparison
  11. Results and Evaluation
  12. Business Insights
  13. Recommendations
  14. Conclusion
  15. Q&A

Presentation should use a professional business style with high-quality visuals, charts, and clean design.

Individual Contribution Sheet

Abdulilah Nabel Alarfaj

  • Project supervision and coordination.
  • Problem definition.
  • Introduction.
  • Business interpretation.
  • Final review and quality assurance.

Abdullah Alansari

  • Literature review.
  • Dataset collection.
  • Data cleaning and preparation.
  • APA referencing.

Yazeed Albalawi

  • Machine learning implementation.
  • Model evaluation.
  • Data visualization.
  • Presentation preparation.

Joint Responsibility

  • Final report review.
  • Presentation delivery.
  • Viva and discussion preparation.
Expected Deliverables
  1. Final Report (3,000–4,000 words).
  2. Dataset file.
  3. Machine Learning analysis files/code.
  4. Individual Contribution Sheet.
  5. Professional PowerPoint Presentation.
  6. APA 7 Reference List.
  7. Turnitin-ready submission.

Please ensure the final work is written at postgraduate (MBA) level, follows academic standards, demonstrates critical analysis, and fully satisfies the MGT632 assessment rubric for maximum marks.