A Structured Approach to Data Mining

List of Figures
List of Tables
Foreword
Preface
Introduction

1. Introduction
   The Roots of Data Mining
   Setting the Context: The Boundaries of Data Mining
   Distinguishing Artificial Intelligence, Data Mining, Machine Learning, and Deep Learning
   Data Mining Process and Its Core Phases
   The Concept of “Model” in Data Mining
   Structure of This Book
2. Problem Understanding
   Overview
   Stakeholder Involvement and Domain Knowledge Integration
   Objective and Problem Formulation
   Critical Questions in Problem Understanding
   The ProFUMe Methodology
   Conclusion
3. Data Understanding
   Overview
   How Data Understanding Impacts Subsequent
   Data Mining Phases
   Data Understanding Through EDA
   Data Structure
   Data Distribution
   Data Quality
   Conclusion
4. Data Preprocessing
   Overview
   Importance of Data Preprocessing
   Core Tasks of Data Preprocessing
   Methods for Handling Missing Values
   Methods for Addressing Outliers
   Methods for Handling Inconsistent Data
   Methods for Solving Irrelevant Data
   Methods for Addressing Duplicate Data
   Methods for Addressing Imbalanced Data
   Encoding Methods for Addressing Machine Learning
   Algorithm Suitability
   Conclusion
5. Data Modelling (Introduction)
   Overview
   Supervised Learning Approach
   Unsupervised Learning Approach
   Unsupervised Learning Tasks: Clustering and Association Rule Mining
   Semi-Supervised Learning
   Comparison of Supervised, Unsupervised, and Semi-Supervised Approaches
   Machine Learning Approaches, Techniques, and Algorithms
   Periodicity of Data Modelling
   Conclusion
6. Data Modelling (Decision Trees)
   Overview
   Types of Decision Trees
   Fundamental Concepts of Decision Trees
   Decision Tree Construction Algorithms
   Decision Tree Algorithms and Their Considerations
   Strengths and Limitations of Decision Trees
   Conclusion
7. Data Modelling (Regressions)
   Overview
   Fundamental Concepts of Regressions
   Types of Regression Techniques
   Examples with Datasets for Different Regression Techniques
   Variable Selection in Regression Models
   Regression Assumptions in Statistical and Machine Learning
   Data Modelling
   Considerations for Regression Algorithm Selection
   Conclusion
8. Data Modelling (Neural Networks)
   Overview
   Neural Networks as the Foundation of Deep Learning
   Fundamental Architecture and Concepts
   Types of Neural Networks
   Neural Network Architectures in Supervised and Unsupervised Learning
   Conclusion
9. Data Modelling (Clustering)
   Overview
   Fundamental Concepts of Clustering
   Data Points Assignments
   Types of Clustering Techniques
   Overview of Clustering Algorithms
   Determining the Number of Clusters
   Applying Clustering Concepts with Example Dataset
   Feature Scaling in Clustering
   Assessing Clustering Model Quality
   Considerations in Selecting Clustering Techniques
   Conclusion
10. Data Modelling (Association Rules)
    Overview
    Fundamental Concepts of Association Rules
    Types of Association Rules
    Considerations in Selecting Association Rules Algorithms
    Conclusion
11. Data Modelling (Ensemble Models)
    Overview
    Fundamental Concepts of Ensemble Models
    Architectures of Ensemble Models
    Existing Algorithms and Implementations for Ensemble Models
    Considerations in Selecting an Ensemble Architectural Strategy
    Conclusion
12. Model Evaluation
    Overview
    Model Fit and Generalisation
    Model Performance
    Model Complexity and Interpretability
    Sampling Techniques for Model Validation
    Feature Importance in Model Evaluation
    Efficiency
    Robustness
    Additional Considerations for Model Deployment
    Conclusion
13. Data Mining Ethics and Emerging Considerations
    Overview
    Ethical Foundations in Data Mining
    Ethical Data Mining Lifecycle
    Ethics Guidelines, Policies and Law
    Evolving Ethics in Data Mining
    Ethical Challenges in Data Mining for Generative AI
    Conclusion

Exercises
References
Index

Chua Hui Na is Professor at Sunway University, Malaysia, specialising in data mining, applied machine learning, and responsible AI. With extensive industry experience in data engineering and analytical systems development, she is involved in nationally funded and industry-driven research and development initiatives that have led to multiple intellectual property and copyright filings.