Chat with us, powered by LiveChat

Applied Data Mining

This subject is available under ICMS undergraduate degrees, please click the button below to find an undergraduate course for you.

Subject Code:

DAT201A

Subject Type:

Specialisation 

Credit Points:

3 credit points

Pre-requisite/Co-requisite: 

DAT102A Business Data Analytics 

Course level of study pre-requisite: a total of 12 credit points including ICT101A, ICT102A, ICT103A and DAT101A from level 100 core subjects prior to enrolling into level 200 core and specialisation subjects. 

Subject Level:

200 

Subject Rationale:

The ability to mine data has become one of the most essential skills required for success in the era of digital revolution and big data. Mining data in this sense refers to a set of analytical approaches to detect, explain, and assess patterns, relationships, and changes in different forms of data. As a result, data mining is an increasingly sought-after skill in today’s job market across all industries.  

This subject offers a comprehensive introduction into the data mining analytical skills. It includes predictive and descriptive models in data mining and equips students with contemporary theoretical knowledge and practical skills of the primary data mining tasks including regression, classification, clustering, summarisation, dependency modelling and deviation detection. Students will learn how to perform these tasks and apply them to real world problems. As a result, this subject lays the foundation for more advanced understanding of big data analytics where data mining and advanced computing work in tandem to generate insights from big data. 

Learning Outcomes:

a) Explain the concept of data mining and its difference in comparison to traditional data analytics methods.

b) Evaluate data mining techniques, tools, and their application in solving real business problems.

c) Develop data mining plans to address specific business issues.

d) Apply appropriate data mining techniques to generate insights from various forms of data to support business decision making.

e) Analyse the emerging data mining trends and their relevance in specific business problems.

 

Student Assessment:

Broad Topics to be Covered:

Topic: 
Week 1: Introduction to Data Mining  

  • Introduction to and history of data mining 
  • Data mining and business intelligence 
  • Data mining and business analytics  
  • Data mining and big data 
Week 2: Process of Data Mining 

  • Overview of data mining process  
  • Steps in data mining projects 
  • Foundation of programming in data mining process 
  • Data partitions 
  • Basics of predictive modelling 
Week 3: Attributes, Measurements and Pre-processing of Data 

  • Types of attributes 
  • Attributes measurement principles 
  • Types of data sets  
  • Pre-processing of data: sanity check and data quality 
  • Noise and artefacts 
Week 4: Classification Techniques in Data Mining  

  • General framework for classification  
  • Decision tree classifiers 
  • Model overfitting 
  • Model selection and evaluation 
Week 5: Association Analysis in Data Mining 

  • The Apriori principle and algorithm 
  • Rule generation 
  • F-P growth algorithm 
  • Evaluation of association rules 
Week 6: Cluster Analysis in Data Mining 

  • Principles of clustering 
  • Types of clusters  
  • K-mean cluster 
  • Agglomerative Hierarchical Clustering 
  • Clustering evaluation 
Week 7: Alternative Classificatory Methods in Data Mining 

  • Rule Based classifier 
  • Nearest Neighbour classifier 
  • Naïve Bayes classifier 
Week 8: Logistic Regression 

  • Logistic regression model 
  • Predictive modelling with logistic regression 
  • Parameter estimation 
  • Logistic regression model evaluation 
  • Multiclass classification 
Week 9: Forecasting Methods in Data Mining  

  • Introduction to time series  
  • Popular forecasting algorithms 
  • Data partitioning 
  • Performance evaluation  
  • Naïve forecast  
Week 10: Anomaly Detection Techniques 

  • Definition of an anomaly 
  • Types of anomalies 
  • Proximity-based detection methods 
  • Clustering based detection methods  
Week 11: Future of Data Mining  

  • Deep learning  
  • Intelligent discoveries  
  • Model optimisation 
  • Revision and reflection  

Please note that these topics are often refined and subject to change so for up to date weekly topics and suggested reading resources, please refer to the Moodle subject page.