A core ART competency goes hand in hand with hiring a lawyer to discuss significant developments in client representation. Model rule 1.4 provides that the lawyer`s duty to disclose requires the lawyer to “reasonably consult with the client on the means by which the client`s objectives are to be achieved” and “explain a matter to the extent reasonably necessary for the client to make informed decisions”. In a case requiring a lot of documentation, communication with a client should include a discussion of the pros and cons of using ART. For example, benefits may include cost savings and efficiency that lead to more accurate results, while disadvantages may include controversies with opposing litigants arising from the use of ART. Without at least a basic understanding of the TRE, lawyers will not be able to communicate the risks and benefits of the TAT to clients, allowing clients to make informed decisions about the use of the TRE. Boot properly by training the system correctly. Predictive coding has a garbage-in, garbage-out application. The software encodes the correct and incorrect instructions, regardless of the information provided by the trainer. Start by carefully selecting a sample of relevant and irrelevant documents. This will be your starting set for software training. It`s also important to take a close look at your audit team.

These should be your most experienced lawyers with a lot of experience to make accurate decisions. It is useful to work with two or three experts rather than a single auditor to ensure the quality of the system and avoid impartial training. A Subject Matter Expert Group (EMS) should identify a representative sample of documents to be used as a starting set or sample of the document set to be reviewed. With predictive coding software, every document in the set should be coded as relevant or irrelevant by an SME. In this article, we discuss what predictive coding is and how we see it being used in the context of New Zealand Discovery in the future. Technology-assisted examination (TRE), also known as predictive coding or computer-based examination, has been defined as “a process of prioritizing or encoding a collection of documents using a computerized system that uses the human judgments of one or more subject matter experts for a smaller set of documents, then extrapolates these judgments to the remaining collection of documents.” Maura R. Grossman and Gordon V. Cormack, “The Grossman-Cormack Glossary of Technology Assisted Review,” 7 Fed. Courts L. Rev.

1 (2013). When used correctly, ART can result in drastic savings for clients in paper-intensive cases and provide more accurate results. However, as the use of ART grows, practitioners need to be aware of the relevant ethical pitfalls that may arise. If you are faced with a significant amount of documents that need to be reviewed. As mentioned in Pyrrho Investment`s decision, the volume of documents to be reviewed was huge – about 3.1 million documents after deduplication. Due to the volume of documents to be reviewed, predictive coding was seen as more efficient and cost-effective, saving hundreds or even millions of pounds. For once, the technology behind predictive coding was too complex, requiring statistical sampling experts to run the software. Hiring these professionals has been difficult and costly, not to mention the software itself and the associated costs (implementation, training, etc.). About the authors: Rishi Chhatwal, Robert Keeling, Peter Gronvall, and Nathaniel Huber-Fliflet are frequent contributors to research on machine learning in the legal field. Together, they conducted thousands of experiments to evaluate the effectiveness of predictive legal data modeling and recognize the importance of its role in the eDiscovery process. Predictive coding software involves the use of artificial intelligence programming and mathematical models to analyze electronic documents and find data relevant to the legal case.