Overview
Hello, Below is the instructions for the assignment. Detailed instruction are given in attached file.
Also, you should make a Presentation for the report. Please note that all submissions will be subject to Turnitin scrutiny for similarity and AI-generated content. The permitted similarity limit is 7% Submissions exceeding this threshold may be subject to academic penalties.
You Must provide Turnitin Report for Similarity and AI percentageAssignment Title
Business Decision-Making Using Machine Learning: Analysis of a Real-World Business Proble
Word Count: 2,500–3,000 words Submission Format: MS Word Referencing Style: APA Submission Deadline: 3 July
Academic Integrity Requirements
- The assignment must be the student's own work.
- All sources must be cited using APA.
- A minimum of 10 academic references (journal articles, books, industry reports, and reputable business sources) is required.
- Plagiarism, contract cheating, and unauthorised copying will be penalised according to university regulations.
Assignment Purpose
Modern organisations increasingly use Machine Learning (ML) to support strategic, tactical, and operational decision-making. This assignment aims to develop students' understanding of how ML techniques can improve business decisions through data-driven insights.
Students will identify business problems, examine how machine learning can support decision-making, select appropriate ML techniques, evaluate business implications, and provide managerial recommendations.
Assignment Scenario
Assume you are a Business Analytics Consultant hired by an organisation seeking to improve decision-making through machine learning.
Select ONE of the following business decision-making scenarios:
Option 1: Customer Retention Decision
A company wants to identify customers likely to leave and determine retention strategies.
Option 2: Loan Approval Decision
A bank wants to improve credit approval decisions while reducing loan default risk.
Option 3: Inventory Management Decision
A retail company wants to forecast product demand and optimise inventory levels.
Option 4: Marketing Campaign Decision
An e-commerce company wants to identify customers most likely to respond to promotions.
Option 5: Fraud Investigation Decision
A financial institution wants to identify suspicious transactions requiring investigation.
Option 6: Employee Retention Decision
A company wants to identify employees at risk of resignation and design retention programs.
Option 7: Supply Chain Decision
A manufacturing company wants to predict disruptions and optimise supplier selection.
Assignment Requirements
Section 1: Business Problem and Decision Context (4 Marks)
Task
Describe the selected organisation and explain the business decision that needs improvement.
Include:
1.1 Organisation Background
- Industry
- Products/services
- Market environment
1.2 Business Problem
Explain:
- Current challenges
- Impact on organizational performance
- Why better decisions are required
1.3 Decision-Making Context
Identify:
- Strategic decision
- Tactical decision
- Operational decision
Example
Organisation: Telecommunications Company
Problem: High customer churn rates.
Required Decision: Which customers should receive retention offers?
Decision Type: Tactical and operational decision.
Section 2: Role of Machine Learning in Business Decision-Making (4 Marks)
Task
Explain how machine learning supports business decisions.
Include:
2.1 Machine Learning Overview
Define:
- Machine Learning
- Artificial Intelligence
- Predictive Analytics
2.2 Types of Machine Learning
Explain:
Supervised Learning
Examples:
- Credit scoring
- Churn prediction
Unsupervised Learning
Examples:
- Customer segmentation
- Market Basket Analysis
Reinforcement Learning
Examples:
- Dynamic pricing
- Recommendation systems
2.3 Selected ML Approach
Justify why your chosen approach is suitable.
Section 3: Data Requirements (3 Marks)
Task
Identify the data required for decision-making.
Section 4: Machine Learning Model Selection and Application (4 Marks)
Task
Select one or two ML algorithms suitable for the decision problem.
Include:
4.1 Algorithm Selection
Examples:
Business Decision | ML Technique |
Churn Prediction | Decision Tree |
Credit Approval | Logistic Regression |
Sales Forecasting | Linear Regression |
Fraud Detection | Random Forest |
Customer Segmentation | K-Means Clustering |
Pricing Decision | Reinforcement Learning |
4.2 How the Algorithm Works
Explain in simple terms.
4.3 Decision Support
Explain how managers use model output for decision-making.
Section 5: Business Impact, Ethical Issues and Risks (3 Marks)
Task
Evaluate organisational implications.
5.1 Benefits
Discuss at least five benefits.
Examples:
- Better decision quality
- Reduced uncertainty
- Faster decisions
- Cost savings
- Revenue growth
- Improved customer satisfaction
- Competitive advantage
5.2 Risks and Challenges
Examples:
- Data privacy concerns
- Algorithm bias
- Poor data quality
- High implementation costs
- Cybersecurity threats
- Lack of expertise
5.3 Ethical Considerations
Discuss:
- Fairness
- Transparency
- Accountability
- Responsible AI
- Data protection
Use examples from GCC or international organisations but it must be well known organisations
Section 6: Recommendations and Conclusion (2 Marks)
Recommendations
Provide at least five practical recommendations.
Examples:
- Establish data governance policies.
- Improve data quality management.
- Train employees in data analytics.
- Regularly monitor model performance.
- Implement ethical AI guidelines.
Conclusion
Summarise:
- Business problem
- ML solution
- Expected business value
- Decision-making improvements
Table of Contents
Executive Summary (200 words)
1. Business Problem and Decision Context
2. Machine Learning in Business Decision-Making
3. Data Requirements and Preparation
4. Machine Learning Model Selection and Application
5. Business Impact, Ethical Issues and Risks
6. Recommendations and Conclusion
References
Appendices (if applicable)
Detailed Marking Rubric (20 Marks)
Assessment Criteria | Excellent (80-100%) | Good (70-79%) | Satisfactory (60-69%) | Poor (<60%) | Marks |
Business Problem and Decision Context | Comprehensive explanation with excellent business understanding and decision analysis | Good discussion with minor gaps | Basic discussion | Weak or unclear discussion | 4 |
Understanding of ML and Decision-Making Concepts | Excellent understanding of ML concepts and business relevance | Good understanding | Limited understanding | Major conceptual weaknesses | 4 |
Data Requirements | Thorough identification of data, variables, and preparation techniques | Good coverage | Basic coverage | Inadequate discussion | 3 |
ML Model Selection and Application | Appropriate model selection with strong justification and decision support explanation | Good justification | Partial justification | Poor or incorrect model choice | 4 |
Business Impact, Risks and Ethical Considerations | Critical evaluation with relevant examples | Good analysis | Basic discussion | Limited analysis | 3 |
Recommendations, Conclusion, Presentation and Referencing | Practical recommendations, professional presentation, proper APA referencing | Minor weaknesses | Several weaknesses | Poor organisation and referencing | 2 |
Total | 20 Marks |
Illustrative Example
Topic:
Using Machine Learning for Customer Churn Decision-Making in the Telecommunications Industry
Business Problem
A telecom company loses approximately 15% of customers annually. Customer acquisition costs are increasing, making retention a strategic priority.
Decision Required
Which customers are most likely to leave within the next three months, and what retention actions should be taken?
ML Technique
Decision Tree Classification
Data Variables
- Customer Age
- Monthly Charges
- Contract Type
- Internet Usage
- Customer Tenure
- Customer Complaints
- Payment Method
- Customer Satisfaction Score
- Service Plan
- Churn Status
Expected Model Output
Customer | Churn Probability |
Customer A | 85% |
Customer B | 22% |
Customer C | 78% |
Decision-Making Application
Managers can:
- Offer discounts to high-risk customers.
- Provide loyalty programs.
- Improve customer service interventions.
- Allocate retention budgets more effectively.
Business Benefits
- Reduced customer attrition.
- Increased profitability.
- Better resource allocation.
- Improved customer experience.
- Data-driven managerial decisions.
Ethical Issues
- Protection of customer personal data.
- Avoiding discriminatory decision-making.
- Ensuring transparency in automated decisions.
Recommendation
Deploy the churn prediction model and review model performance quarterly to maintain prediction accuracy and business relevance.