This insights article by Mason Hayes & Curran penned by Gerard Kelly and Jane Bourke is a good belts and braces review regarding the topic of eDiscovery. They cover some simple points around; what eDiscovery is, what it does, what advances are being made etc. They specifically focus on TAR, which is something I have spoken about a number of times.
On many of our cases, we are now utilising Continuous Active Learning (CAL) or TAR 2.0 (as it is commonly known). With a CAL workflow, there is no need for the review of a ‘seed set’ of documents unlike the traditional Predictive Coding model. The technology promotes documents that it thinks are most relevant to the front of the review queue. This means that likely relevant documents are seen earlier by reviewers. This technology really comes into its own on cases with large data sets and tight timeframes.
In the UK, under the new disclosure rules, we see an acceptance of this technology by the courts… but like anything, the key is having an experienced eDiscovery at the helm of the algorithm.
The authors share a useful conclusion, which I would certainly agree with. “All things considered, TAR will not yet entirely replace humans in the discovery process. However, the relentless advancement of the design and capabilities of the software will make it an increasingly vital tool in the lawyer’s toolbox when working on the sort of enormous discovery universes that exist today.”
In a profession where billable hours are all-important, e-discovery can offer a more efficient option in terms of both time and cost when compared to lawyers having to read individual documents. Imagine a large-scale discovery operation without the assistance of artificial intelligence – with a universe containing five terabytes of documents, roughly 375 million pages. Each lawyer now has 75 million documents to review, which at a rate of 50 documents per day, will take 1.5 million days to complete. Now imagine 500 lawyers were assigned such a review, and they worked exclusively on the discovery, allowing them to review 500 documents a day.
https://www.mhc.ie/latest/insights/ai-in-e-discovery-just-how-smart-is-it
