Supervised and Unsupervised Learning for Data Science

The book "Supervised and Unsupervised Learning for Data Science" provides a comprehensive overview of modern learning algorithms, including semi-supervised methods that cover a wide range of clustering and classification solutions for big data applications. It includes case studies and best practices, as well as theoretical models of learning that serve as a valuable reference for professionals and students. The eight chapters of the book address key topics such as discretization, feature extraction and selection, classification, clustering, topic modeling, graph analysis, and their applications. This work is particularly useful for practitioners and graduates dealing with current and future research questions, as well as for educators who wish to present modern approaches to unsupervised and semi-supervised learning in graduate-level seminars. The content is based on selected, extended contributions from the fourth International Conference on Soft Computing in Data Science.