ELE 3909 Cluster Analysis for Business

ELE 3909 Cluster Analysis for Business

Course code: 
ELE 3909
Department: 
Data Science and Analytics
Credits: 
7.5
Course coordinator: 
Rogelio Andrade Mancisidor
Course name in Norwegian: 
Cluster Analysis for Business
Product category: 
Bachelor
Portfolio: 
Bachelor - Programme Electives
Semester: 
2023 Autumn
Active status: 
Active
Level of study: 
Bachelor
Teaching language: 
English
Course type: 
One semester
Introduction

Clustering methods help to design strategies based on customer segments rather than the entire population, in order to better meet customer expectations. We can, for example, design marketing campaigns, avoid customer leakage or assess credit risk more accurately by analyzing clusters in a given population and designing specific strategies for each cluster. Clustering methods are also useful for revealing which similar characteristics subgroups of a population share. 

This course presents different clustering techniques for revealing subgroups within a larger population, as well as methods for analyzing and understanding what characteristics distinguish each group. In addition, the course introduces the idea of dynamic clustering, or time-dependent clustering, in which we learn to track movements between clusters over time.

The focus of the course is practical and analytical, preparing students for jobs as data analysts/scientists or for a master's degree in Data Science for Business or Business Analytics.

Learning outcomes - Knowledge

In this course the students will:

  • Learn the difference between supervised and unsupervised learning
  • Learn how to prepare and/or transform a data set for cluster analysis
  • Get a thorough introduction to different clustering algorithms
  • Learn how to select the optimal number of clusters
  • Learn to analyze the clustering results
  • Understand the differences between clustering and dynamic clustering
Learning outcomes - Skills

After the completion of this course, students will be able to:

  • Prepare data sets, including data representations, for cluster analysis
  • Apply different cluster techniques for a given task
  • Choose the number of clusters using an appropriate metric
  • Use statistical methods to analyse the results 
General Competence

Students should be able to understand the principles of unsupervised learning and how clustering methods can be applied in different applications. A successful student will be able to select a clustering algorithm, carry out an analysis that reveal hidden patterns in the data, or a representation of it, and bring added-value into the application of the analysis. 

Course content
  • Unsupervised vs Supervised learning
  • Key clustering algorithms, including: Hierarchical clustering, K-means, and density-based clustering methods
  • Cluster analysis on different feature spaces
  • Statistical methods to analyze the clusters 
  • Clustering vs Dynamic clustering 
Teaching and learning activities

Lectures and practical exercises that must be solved with a computer using Python. The practical exercises are shared via GitHub. 

Software tools
Software defined under the section "Teaching and learning activities".
Additional information

Please note that while attendance is not compulsory in all courses, it is the student’s own responsibility to obtain any information provided in class.

Qualifications

Higher Education Entrance Qualification

Disclaimer

Deviations in teaching and exams may occur if external conditions or unforeseen events call for this.

Required prerequisite knowledge

EBA 1180 Mathematics for Data Science or EBA 2904 Statistics with programming.

Students who do not have EBA 1180 Mathematics for Data Science or EBA 2904 Statistics with programming, can compensate the requirement with any other similar course in mathematics or statistics.

Assessments
Assessments
Exam category: 
Submission
Form of assessment: 
Written submission
Weight: 
40
Grouping: 
Group (2 - 3)
Duration: 
1 Week(s)
Comment: 
Written home exam. Work in groups of up to three. Requires Python. All exams must be passed to obtain a final grade in the course.
Exam code: 
ELE 39091
Grading scale: 
ECTS
Resit: 
Examination when next scheduled course
Exam category: 
Submission
Form of assessment: 
Written submission
Invigilation
Weight: 
60
Grouping: 
Individual
Support materials: 
  • BI-approved exam calculator
  • Simple calculator
  • Bilingual dictionary
Duration: 
3 Hour(s)
Comment: 
Written school exam. All exams must be passed to obtain final grade in the course.
Exam code: 
ELE 39092
Grading scale: 
ECTS
Resit: 
Examination when next scheduled course
Type of Assessment: 
Ordinary examination
All exams must be passed to get a grade in this course.
Total weight: 
100
Student workload
ActivityDurationComment
Teaching
36 Hour(s)
Seminar groups
9 Hour(s)
Student's own work with learning resources
130 Hour(s)
Group work / Assignments
25 Hour(s)
Sum workload: 
200

A course of 1 ECTS credit corresponds to a workload of 26-30 hours. Therefore a course of 7,5 ECTS credit corresponds to a workload of at least 200 hours.