Practical Fairness: Achieving Fair and Secure Data Models

Shulph Ink Verified independent store

→

This book provides practical guidance for data and AI professionals to develop fair and secure code by covering basic concerns related to data security and privacy, highlighting up -to-date academic research, and discussing legal developments. Format: Paperback / softback Length: 175 pages Publication date: 18 December 2020 Publisher: O'Reilly Media, Inc, USA The growing importance of fairness in data science is becoming increasingly evident. Mounting evidence suggests that the widespread adoption of machine learning and AI in business and government is perpetuating the same biases we aim to combat in the real world. However, when it comes to code, what exactly does fairness mean? This practical book addresses fundamental concerns related to data security and privacy, empowering data and AI professionals to utilize code that is fair, unbiased, and free from discrimination.Numerous realistic best practices are emerging at every stage of the data pipeline, from data selection and preprocessing to closed model audits. Author Aileen Nielsen leads you through the technical, legal, and ethical aspects of creating code that is fair and secure, while highlighting up-to-date academic research and ongoing legal developments related to fairness and algorithms.Identify potential bias and discrimination in data science modelsImplement preventive measures to minimize bias during the development of data modeling pipelinesUnderstand which data pipeline components implicate security and privacy concernsWrite data processing and modeling code that follows best practices for fairnessRecognize the complex interrelationships between fairness, privacy, and data security created by the use of machine learning modelsApply normative and legal concepts relevant to evaluating the fairness of machine learning models Weight: 614g Dimension: 178 x 233 x 23 (mm) ISBN-13: 9781492075738 Show more