LUBS5308M – Business Analytics and Decision Science

University of Leeds | Leeds University Business School

🎯 Course Overview

This module provides practical skills in business analytics and decision science, focusing on solving real business problems through data acquisition, cleaning, and analysis. Students will learn to use tools like Microsoft Excel, R, and Gephi while applying various Multi-Criteria Decision Analysis (MCDA) methods. The module emphasizes hands-on learning through case studies, practical exercises, and real-world applications.

📅 Weekly Lecture Themes & Content Focus

• Week 1: Introduction to BADS
  • Advanced Microsoft Excel features
• Week 2: Decision Science 1 – Classic Methodologies
  • Weighted Sum Method
  • Goal Programming in Excel
• Week 3: Decision Science 2 – Pairwise Comparison Methods
  • Analytic Hierarchy Process (AHP) in Excel
• Week 4: Decision Science 3 – Ideal Point Methods
  • TOPSIS and VIKOR methods in Excel
• Week 5: Databases, Queries & Other Data Sources
  • SQL queries and APIs
• Week 6: Introduction to R
  • Analyzing real UK Police data
• Week 7: Data Pre-Processing & Dealing with Missing Data
  • Using dplyr package
  • Applying missing data methods to Titanic dataset
• Week 8: Big Data Systems
  • Hadoop, MapReduce & Spark
  • Analyzing big data in Microsoft Azure
• Week 9: Clustering 1 – Network Graphing and Visualization
  • Visualizing company email data in Gephi
• Week 10: Clustering 2 – Hierarchical and K-Means Clustering
  • Separating product data using clustering methods in R

📚 Key Readings

• Core Textbook: Foreman, J.W. Data Smart: Using Data Science to Transform Information into Insight (ISBN: 9781118661468)
• R Programming: Kabacoff, R. R in Action (3rd edition)

📝 Assessment

The module is assessed through a 100% coursework assignment consisting of two parts:

• Part 1 (50% – 1,500 words):
  1. Model a warehouse expansion decision using AHP and TOPSIS methods
  2. Summarize data and outputs in Excel
  3. Provide recommendations to the manufacturing company
• Part 2 (50% – 1,500 words):
  1. Handle missing data in Brewdog beer dataset using imputation
  2. Cluster the beers using appropriate algorithm
  3. Present findings in a dendrogram

Evaluation Criteria: Technical accuracy, analytical depth, clarity of presentation, and practical application of methods.

🔍 Assignment Preparation Guide

Key Methods to Apply

• AHP Method: For structuring complex decisions with multiple criteria
• TOPSIS Method: For ideal point-based decision making
• Data Imputation: For handling missing values in datasets
• Clustering Algorithms: For grouping similar data points

Report Structure Tips

1. Introduction: Problem statement and objectives
2. Methods: Explanation of chosen analytical methods
3. Analysis: Step-by-step application of methods
4. Results: Clear presentation of findings
5. Recommendations: Practical business implications

📝 Mock Assignment Brief