Now that we’ve had a chance to recover from Nashville and think about the annual ILTA conference as a whole, one thing stands out – predictive analytics looks like the next major stage in legal practice evolution. Essentially, predictive coding incorporates machine learning into a process to help classify and identify potentially relevant records for review. This is a subset of a larger science call Predictive Analytics.
What we saw at ILTA was the application of Predictive Analytics to more than just document discovery. One vendor was touting their ability to proofread documents and actually learn the author’s writing style. Another vendor demonstrated a product that can review all of a corporation’s contracts during merger negotiations in order to discover if any of them contain surprises.
We reported a couple of weeks ago about IBM’s Watson computer and how it can now develop logical arguments. Several leading edge software developers at ILTA expected to incorporate that type of Predictive Analytics into their systems within the next two years.
Lawyers use their intuition and experience when practicing law. Now they can use technology to help make their “predictions” much more accurate.
Wednesday night at ILTA was set aside as a “free” night for attendees, giving vendors an opportunity to host their corporate parties. Being in Nashville, the locations ranged from Tennessee bourbon bars to the Country Music Hall of Fame. The latter included a tour of the museum, displaying both the instruments and the people who played them, and showing how a guitar in the right hands could produce wonderful music.
One of the most interesting sessions at ILTA was presented by Patrick Oot of the eDiscovery Institute. He discussed the preliminary findings of a very comprehensive study on the accuracy of machine learning technology vs. human review. The study, involving about 1.7 million records from a real litigation, was funded by Oracle and the volunteered resources of the participants. Although the human review results have not yet been published, the machine learning phase is complete, and some interesting information has come to light.
The costs ranged from $45,000 to over $800,000. The results, measured in recall and precision, were similarly all over the chart. The best results were provided by a vendor whose overall cost was in the bottom third, but was not the lowest. The results from the most expensive vendor were rather poor.
The key piece of information from this study is that the technology is just a tool. Just as with country music, the human process wrapped around the tool is what determined success.
The Wortzmans team is now in its third day at ILTA in Nashville. We’ve met many vendors and attended a number of educational seminars, but there is always more to do.
Here are a few innovations and new systems:
Microsoft has entered the legal case management arena with their Matter Center add on for SharePoint 2013. Although still at the beta stage, it looks like it might get legal record managers to start considering Sharepoint as a viable DMS system.
Some vendors are embracing predictive analytics in different ways, including one vendor touting their proof reading software that learns writing styles, and a DMS system that learns how to automatically classify emails into appropriate legal files.
New wearable technology is also being exhibited, including a ring that, when worn, will automatically authenticate the wearer to other devices, such as a smartphone, laptop, or a building security system.
The overriding theme of the conference is that technology advances, while disruptive, can be a vehicle for positive change.