Rely on the most comprehensive, up-to-date legal content designed and curated by lawyers for lawyers
Work faster and smarter to improve your drafting productivity without increasing risk
Accelerate the creation and use of high quality and trusted legal documents and forms
Streamline how you manage your legal business with proven tools and processes
Manage risk and compliance in your organisation to reduce your risk profile
Stay up to date and informed with insights from our trusted experts, news and information sources
Access the best content in the industry, effortlessly — confident that your news is trustworthy and up to date.
Find up-to-date guidance on points of law and then easily pull up sources to support your advice with Lexis PSL
Check out our straightforward definitions of common legal terms.
Our trusted tax intelligence solutions, highly-regarded exam training and education materials help guide and tutor Tax professionals
Access our unrivalled global news content, business information and analytics solutions
Insurance, risk and compliance intelligence using big data, proprietary linking and advanced analytics.
A leading provider of software platforms for professional services firms
In-depth analysis, commentary and practical information to help you protect your business
LexisNexis Blogs shed light on topics affecting the legal profession and the issues you're facing
Legal professionals trust us to help navigate change. Find out how we help ensure they exceed expectations
Lex Chat is a LexisNexis current affairs podcast sharing insights on topics for the legal profession
Discuss the latest legal developments, ask questions, and share best practice with other LexisPSL subscribers
Predictive coding is a method of technology assisted review (TAR) used to assess the relevance of high volumes of documents for purposes of electronic disclosure (e-disclosure).
Predictive coding uses a combination of keyword search and iterative computer learning to rank the relevance of each individual document.
It starts off with a human operator (such as a lawyer) who understands how to grade the relevance of a legal document for purposes of disclosure. They will perform a search for relevant documents in an initial ‘seed set’ and grade these manually, providing a relevance mark for each (eg on a scale of 1 – 10). The software will analyse their manual grading to optimise its own search engine AI. This process will be repeated multiple times to enhance accuracy.
Once the human operator has ‘trained’ the AI, the predictive coding system can be left to trawl through the bulk of documents automatically, with just the occasional verification for accuracy by lawyers. In this way, thousands of documents can be graded for relevance (for purposes of disclosure) in a fraction of the time it would take a team of paralegals.
The primary benefits of predictive coding are speed and overall cos
Access this article and thousands of others like it free by subscribing to our blog.
Read full article
Already a subscriber? Login
0330 161 1234