Firstly, what
does predictive coding do differently than keyword searching?
Why
do predictive coding proponents have the burden of proof to rebut the presumption that predictive coding is unreliable?
Apr. 18, 2013)-RRB-(«Biomet I»), the court refused to require the responding party to
do predictive coding on the entire corpus of its documents, instead allowing it to rely on the keyword searching it used initially to filter the material prior to predictive coding.
Not exact matches
In pretty much all matters it's worth
doing some testing to see if
predictive coding will be helpful.
So, picking up on the ECA and
predictive coding themes, I don't think technology will eliminate review lawyers.
We've been working with a range of clients, including regulators, law firm partners and corporate legal teams to help them understand: first, the
predictive coding process as a whole from start to finish, and what that looks like for their particular matter; and second, some basic elements such as precision and recall, so they don't get bogged down in the nuts and bolts of the data science.
Or
predictive coding that requires far fewer lawyer hours to
do eDiscovery work and allows them more time to explore and test new opportunities with their clients.
RF: I don't draw that big a distinction between ECA and
predictive coding.
The bottom line: I don't believe we're anywhere near the Hal 9000 / Space Odyssey scenario or a comprehensive
predictive coding process eliminating the use of attorneys during the review.
Ari: [29:16] Joe, on that point, it was interesting, when we were
doing the research, that 88 percent of the people, both in - house counsels and law firm lawyers, wanted to learn more about measuring and understanding the effectiveness of
predictive coding.
It has been widely publicised that the Pyrrho decision
did not involve a contested use of
predictive coding: the parties had agreed upon its use and were seeking the court's approval.
Whether we call these software programs «
predictive coding,» «technology - assisted review» or something else entirely, how
do you know that they are right for you as a cautious and risk - averse in - house lawyer?
«Legal teams are eager to use
predictive coding and reduce the overall cost of e-discovery, but they will only
do it if it's defensible,» said Barry Murphy, founder of the e-Discovery Journal.
As stated above, small cases
do not make good
predictive coding candidates.
But it
does not
do true TAR or
predictive coding, as I understand it.
He then explains
predictive coding in its simplicity: to feed a computer program information based on discovery attorneys have already
done until the computer can accurately predict which information is important.
If that
does not inspire GCs to make the investment to rebut the
predictive coding unreliability presumption, what will?
My first thought:
predictive coding should be one screening tool — but like artificial intelligence, it is «artificial» — at some point, there are subtle issues that even humans view differently — don't reasonable people disagree?
All of the panelists agreed that whether or not
predictive coding is being used on a matter, keywords / search terms still have a useful place in the e-discovery process, as
do other analytics tools including de-duplication and email threading.
The court evaluated 10 factors in favor of use, including proportionality, and
did not list a single factor weighing against the use of
Predictive Coding.
For these types of matters,
predictive coding can help get the job
done quickly, while analytics can offer the confidence that the company's response is thorough.
Vound prides itself on offering features that get the job
done and not in marketing to industry catch phrases such as
predictive coding, Information governance or cyber security.
A
predictive coding platform, when applied and managed correctly, can and will
do a much better job of finding relevant documents within your data set than a keyword search possibly could.
Many legal teams don't have the time or energy to build a case for why a
predictive coding tool is necessary, so they stick with the status quo.
According to Exterro's 2015 Federal Judges Survey on E-Discovery Best Practices and Trends, 45 % of the responding judges said that they only «somewhat agreed» that
predictive coding is employed with regularity in cases, while 41 % didn't agree with the statement at all.
He uses
predictive coding to learn human behaviour, then applies this to what he learns and assimilates feedback to learn from what he
does.
Lowry acknowledges that not every lawyer will need to write prose and
code, but they
do foresee the need to complement next - generation lawyers with these skills, in addition to being able to apply a deeper level of understanding of core technology such as DLT / blockchains, machine learning, and
predictive analytics.
He looks for innovation above all else, noting that while all firms might say they're innovative, he checks things such as if e-discovery is
done the old - fashioned way or whether they have the capacity to leverage AI and
predictive coding.