Â鶹´«Ã½AV

Professors at UC Berkeley and at the University of Utah are thrilled to announce the online release of their "Veridical Data Science: The Practice of Responsible Data Analysis and Decision Making" (), an essential resource for producing trustworthy data-driven results.

Veridical Data Science (VDS) demonstrates how to use the principles of predictability, computability, and stability (PCS) to create and evaluate trustworthy data-driven results by conducting stress tests at every stage of the data science life cycle (DSLC), from problem formulation and data cleaning to modeling and the communication of results. 

VDS arose from the graduate statistics class (STAT 215A) that Yu has taught for many years at Berkeley and has evolved to embody her research philosophy. They are so excited to finally be able to share this book and we hope that it will change the practice of data science for the better. The book is a useful resource for data science, statistics, and applied ML classes as one of the textbooks (together with a traditional book) or as supplementary reading for students. It is intended for upper division level and beginning graduate levels and for domain scientists to enter data science.