Course Objectives

  • Be able to understand the key concepts of data mining techniques, including data preprocessing, data warehousing and cube, frequent pattern mining, classification, and clustering.
  • Be able to apply the key data mining techniques to realistic settings, evaluate and analyze the mining results.


Week Topic
1 Introduction to Data Mining , Data Objects and Types, Central Tendency,    Dispersion and Correlation, Normal Distribution Hypothesis Testing, Visualization, Similarity Measures Part1 Similarity Measures Part 2, KL Divergence , Data Quality, Cleaning, and Integration
2 Data Reduction , Data Transformation, Dimensionality Reduction, Principal Component Analysis (PCA), Pattern Discovery Basics, Closed and Maximal Patterns, Pattern Discovery Methods: Apriori, FPGrowth , Apriori Improvements: Partitioning and Hashing, and ECLAT , Mining Closed Patterns
3 Evaluation, Mining Diverse Frequent Patterns
4 Sequential Pattern Mining, Graph Pattern Mining, Pattern Mining Applications: Software Bug Mining
5 Constraint-Based Mining, Pattern Mining Applications: Mining Quality Phrases from Text Data
6 Exam 1
7 Cluster Analysis Introduction , Partitioning-based Methods: K-Means, K-Means Initialization, K-Medoid , K-Medians and K-Modes, Kernel K-Means,
8 Hierarchical Clustering: Basic Concepts, Hierarchical Clustering Methods, Density-based and Grid-based Clustering Methods
9 Probabilistic Model-based Clustering Methods, Validation
10 Exam 2
11 Decision Tree, Bayes Classifier and Bayesian Networks
12 Model Evaluation, Selection and Improvements, Classification with Weak Supervision
13 Linear Classifer and Support Vector Machines, Neural Networks and Deep Learning
14 Pattern-Based Classification and K-Nearest Neighbors
15 Exam 3