Predictive coding, also called technology-assisted review or TAR, uses machine learning and human feedback to find relevant documents. This collection brings together Ralph Losey’s writing on active learning, search quality, validation and practical review methods.
The articles preserve the development of this work before the November 2022 shift toward generative AI, along with later reflections. Original terminology and publication dates remain visible. Historical law and software should be checked before present-day use.
Explore the collection
108 catalog entries are currently linked to predictive coding, TAR and search validation. Use the full collection to filter by year or find a specific title.
-
Second Grader Version by Chat GPT of the Blog Earlier Today “Four Generations of Predictive Coding Software, from 2009 to Today” (February 2023)
-
Four Generations of Predictive Coding Software, the Background and History of Predictive Coding (February 2023)
-
Chat GPT Helps Explains My Active Machine Learning Method of Evidence Retrieval (January 2023)
-
A Buddhist AI – “The DUDE” – Explains the Eight Steps of Hybrid Multimodal Document Review with Help from a Human Lawyer (January 2023)
-
Transparency in a Salt Lake TAR Pit? (November 2018)
-
Do TAR the Right Way with “Hybrid Multimodal Predictive Coding 4.0” (October 2018)
-
TAR Course Expands Again: Standardized Best Practice for Technology Assisted Review (February 2018)
-
Iterated Four-Step Work Flow for Active Machine Training to Help Attorneys Locate Relevant Evidence (January 2018)
-
Analysis of Important New Case on Predictive Coding by a Rising New Judicial Star: “Winfield v. City of New York” (December 2017)
-
WHY I LOVE PREDICTIVE CODING: Making Document Review Fun Again with Mr. EDR and Predictive Coding 4.0 (December 2017)
-
New Homework Added to the TAR Course and a New Video Added to AI-Ethics (September 2017)
-
Mark Zuckerberg and the Hacker Way: Be Open and Build Social Value (More New Videos Added to the TAR Course) (July 2017)