Data Mining: Concepts and Techniques

Study notes based on Data Mining: Concepts and Techniques (3rd ed., Han, Kamber, Pei).

These notes cover the core course material across data understanding, preprocessing, pattern mining, classification, clustering, outlier analysis, and mining text/web data. Each chapter below focuses on the key definitions, algorithms, and formulas you need for exams.

Chapters

• Chapter 1: Introduction — Why data mining, KDD process, multidimensional view, data mining functions, major issues
• Chapter 2: Getting to Know Your Data — Attribute types, central tendency & dispersion, data visualization, similarity/distance measures
• Chapter 3: Data Preprocessing — Data quality, cleaning, integration, reduction (PCA, histograms, sampling), transformation & discretization
• Chapter 4: Data Warehousing and OLAP — DW concepts, data cube, star/snowflake schemas, OLAP operations, attribute-oriented induction
• Chapter 5: Frequent Pattern Mining (Basic) — Support/confidence, Apriori, FP-growth, ECLAT, interestingness (lift, χ², null-invariance)
• Chapter 6: Frequent Pattern Mining (Advanced) — Multi-level/multi-dimensional, quantitative, rare & negative patterns, constraint-based mining, colossal patterns
• Chapter 7: Classification (Basic) — Decision trees (ID3, C4.5, CART), Naïve Bayes, rule-based, model evaluation (confusion matrix, ROC)
• Chapter 8: Classification (Advanced) — Bayesian networks, backpropagation, SVM, associative & lazy learners, multiclass/semi-supervised/active/transfer learning
• Chapter 9: Cluster Analysis (Basic) — Partitioning (k-means, k-medoids), hierarchical, DBSCAN/OPTICS, grid-based, evaluation
• Chapter 10: Cluster Analysis (Advanced) — Fuzzy/probabilistic (EM), high-dimensional (subspace, bi-clustering, spectral), graph clustering (SCAN), constraints
• Chapter 11: Outlier Analysis — Global/contextual/collective outliers, statistical, proximity (LOF), clustering & classification approaches, high-D outliers
• Chapter 12: Mining Text Data — TF-IDF, cosine similarity, text clustering, topic modeling (PLSA/LDA), text classification, novelty detection
• Chapter 13: Mining Web Data — Web crawling, search indexing, ranking (PageRank, HITS), recommender systems, web usage mining