Bøger af Lior Rokach

This book is a major update to the very successful first and second editions (2005 and 2010) of Data Mining and Knowledge Discovery Handbook. Since the last edition, this field has continued to evolve and to gain popularity. Existing methods are constantly being improved and new methods, applications and aspects are introduced. The new title of this handbook and its content reflect these changes thoroughly. Some existing chapters have been brought up to date. In addition to major revision of the existing chapters, the new edition includes totally new topics, such as: deep learning, explainable AI, human factors and social issues and advanced methods for big-data. The significant enhancement to the content reflects the growth in importance of data science. The third edition is also a timely opportunity to incorporate many other changes based on peers and students¿ feedback.This comprehensive handbook also presents a coherent and unified repository of data science major concepts, theories, methods, trends, challenges and applications. It covers all the crucial important machine learning methods used in data science.Today's accessibility and abundance of data make data science matters of considerable importance and necessity. Given the field's recent growth, it's not surprising that researchers and practitioners now have a wide range of methods and tools at their disposal. While statistics is fundamental for data science, methods originated from artificial intelligence, particularly machine learning, are also playing a significant role.This handbook aims to serve as the main reference for researchers in the fields of information technology, e-Commerce, information retrieval, data science, machine learning, data mining, databases and statistics as well as advanced level students studying computer science or electrical engineering. Practitioners working within these related fields and data scientists will also want to purchase this handbook as a reference.

SpringerBriefs present concise summaries of cutting-edge research and practical applications across a wide spectrum of fields. Featuring compact volumes of 50 to 100 pages (approximately 20,000- 40,000 words), the series covers a range of content from professional to academic. Briefs allow authors to present their ideas and readers to absorb them with minimal time investment. As part of Springer¿s eBook collection, SpringBriefs are published to millions of users worldwide. Information/Data Leakage poses a serious threat to companies and organizations, as the number of leakage incidents and the cost they inflict continues to increase. Whether caused by malicious intent, or an inadvertent mistake, data loss can diminish a company¿s brand, reduce shareholder value, and damage the company¿s goodwill and reputation. This book aims to provide a structural and comprehensive overview of the practical solutions and current research in the DLP domain. This is the first comprehensive book that is dedicated entirely to the field of data leakage and covers all important challenges and techniques to mitigate them. Its informative, factual pages will provide researchers, students and practitioners in the industry with a comprehensive, yet concise and convenient reference source to this fascinating field.We have grouped existing solutions into different categories based on a described taxonomy. The presented taxonomy characterizes DLP solutions according to various aspects such as: leakage source, data state, leakage channel, deployment scheme, preventive/detective approaches, and the action upon leakage. In the commercial part we review solutions of the leading DLP market players based on professional research reports and material obtained from the websites of the vendors. In the academic part we cluster the academic work according to the nature of the leakage and protection into various categories. Finally, we describe main data leakage scenarios and present for eachscenario the most relevant and applicable solution or approach that will mitigate and reduce the likelihood and/or impact of the leakage scenario.

This book explores a proactive and domain-driven method to classification tasks. This novel proactive approach to data mining not only induces a model for predicting or explaining a phenomenon, but also utilizes specific problem/domain knowledge to suggest specific actions to achieve optimal changes in the value of the target attribute. In particular, the authors suggest a specific implementation of the domain-driven proactive approach for classification trees. The book centers on the core idea of moving observations from one branch of the tree to another. It introduces a novel splitting criterion for decision trees, termed maximal-utility, which maximizes the potential for enhancing profitability in the output tree. Two real-world case studies, one of a leading wireless operator and the other of a major security company, are also included and demonstrate how applying the proactive approach to classification tasks can solve business problems. Proactive Data Mining with Decision Trees is intended for researchers, practitioners and advanced-level students.

Decision trees have become one of the most powerful and popular approaches in knowledge discovery and data mining, the science and technology of exploring large and complex bodies of data in order to discover useful patterns. Dedicated to the field of decision trees in data mining, this book covers various aspects of this technique.