Singapore University of Social Sciences

Association and Clustering (ANL305)

Applications Open: 01 April 2020

Applications Close: 14 June 2020

Next Available Intake: July 2020

Course Types: Modular Undergraduate Course

Language: English

Duration: 6 months

Fees: To be confirmed

Area of Interest: Business Administration

Schemes: Alumni Continuing Education + (ACE+), Lifelong Learning Credit (L2C)

Funding: SkillsFuture, Union Training Assistance Programme (UTAP)


Synopsis

The course introduces key principles of association and clustering from an applied perspective, but with emphasis on merits and limitations of algorithms when employed in different situations. By the end of this course, participants should appreciate how algorithms are applied in different contexts, be able to execute the relevant computer commands for solving problems; interpret the generated solutions and provide insightful discussion on topics.

Level: 3
Credit Units: 5
Presentation Pattern: Every July

Topics

  • Association Rule Mining
  • Apriori Algorithm and Rule Evaluation Measures
  • Association Visualisation
  • Continous Association Rule Mining Algorithm (CARMA)
  • Sequence Pattern Mining
  • Sequence Pattern Mining using modeller
  • Introduction to Clustering
  • Partitional and Hierarchical Clustering
  • Two-Step Algorithms
  • Self-Organising Maps
  • Practical Clustering Process
  • Case Studies in Clustering

Learning Outcome

  • Discuss various aspects of association analysis, such as concepts, rule evaluation measures, advantages and limitations.
  • Compare and contrast association rule mining algorithms.
  • Distinguish sequential pattern mining from association rule mining.
  • Discuss various aspects of clustering analysis, such as concepts, cluster validation, proximity measures, advantages and limitations.
  • Compare and contrast advanced and traditional clustering algorithms.
  • Construct an association rule mining solution, interpret and evaluate the rules.
  • Implement a solution for a sequential pattern mining problem.
  • Evaluate the suitability of rule mining methods for a given problem.
  • Execute hierachical clustering, K-means, Self-Organising Map and Two-Step clustering.
  • Design a clustering analysis solution, verify and interpret clustering solutions.
  • Evaluate the suitability of a clustering method for a given problem.
  • Implement a clustering analytics solution to a business problem.
  • Verify the clustering solutions with appropriate criteria and framework.
  • Apply the above-mentioned data mining tasks using the software package specified in this course.
Back to top
Back to top