Gene expression data analysis is one of the most valuable and relatively mature application areas of big data. This book is a work on cancer gene expression data mining and machine learning algorithms, comprehensively and systematically explaining the models, algorithms, platforms, and examples of cancer gene expression data learning. The book consists of 10 chapters and is divided into 4 parts. The first part includes chapters 1-3, which introduce the basic knowledge of cancer gene expression data, preprocessing techniques, and commonly used data analysis platforms; Part 2 (Chapters 4-6) introduces key gene screening, class imbalance data sampling, and cancer pathogenic gene prediction methods; Part 3 (Chapters 7-8) is about sequence based gene association rules and local pattern mining techniques. Chapter 7 is about gene association analysis mining frequent atomic sequences, and Chapter 8 is about mining and querying order-preserving submatrixes; Part 4 (Chapters 9-10) is the classification and novel class recognition algorithm for cancer gene expression data.