Legal Analytics Is Getting Even Better: An Interview With Lex Machina CEO Karl Harris

Learn more on the latest additions and enhancements to Lex Machina's powerful Legal Analytics platform, including Appellate Analytics and Legal Analytics API.

karl_harris_image_HS

Karl Harris

Data has forever changed the way the legal industry approaches and practices law. In the area of litigation, Lex Machina’s Legal Analytics platform has fundamentally altered the landscape of how lawyers build strategies and make case decisions, and they’re continuing to make their invaluable tools and unrivaled insights even better.

We recently sat down with Karl Harris, CEO of Lex Machina, to discuss some of the latest additions and enhancements to its powerful Legal Analytics platform, including Appellate Analytics, State Motion Metrics, and the Legal Analytics API. 

What is Appellate Analytics and why was it created?

Appellate Analytics gives users the ability to make data-driven decisions around cases that ultimately end up on appeal and about those appeals themselves. It shows how a judge is likely to behave in a certain scenario. Is a particular district court judge likely to be appealed and, if so, what’s likely to happen on that appeal? It’s about seeing the litigation lifespan of a federal district court case. It completes the story of the district court cases on our Legal Analytics platform.

Since we started Lex Machina in 2012, customers have been asking for analytics on appeals. Adding Appellate Analytics is the culmination of a journey for us and gets us to where we wanted to be for almost 10 years now. Our mission is to bring Legal Analytics to all areas of law. We got there in federal district court, and now we’re able to put the appellate umbrella on top of everything.

Why is Lex Machina so uniquely well-suited to tackle appellate cases?

Lex Machina is a unique solution in that we have what we call outcome-based litigation analytics – the ability to answer all questions about case resolution, damages, findings, and more is exclusive to Lex Machina. Being able to say what happened on appeal with those cases is central to really determining what happened in federal district court. Given that we’re the only solution that has the data to determine those outcomes for federal district court, we’re naturally positioned to be the only solution that can say what happened to those cases on appeal. It’s the same outcome-based analytics at work.

How does Appellate Analytics fit into the bigger picture of the Legal Analytics platform?

One of the things we’re really excited about is that, if you know how to use Lex Machina, then you already know how to use Appellate Analytics. It’s the same user interface. We have unique data for appeals, but it’s the same tool. It just extends the story all the way to cases on appeal and completes it.

What is State Motion Metrics and why was it created?

State Motion Metrics focuses on what happens when a state court judge issues an order related to a motion. It covers outcomes for 37 different kinds of motions in state court. Again, on the theme of completing the story, State Motion Metrics goes beyond just telling the outcomes for state court cases that go to trial and also includes outcome information on cases that were disposed of on motion practice, which is very common. It allows us to extend the outcome-oriented story of litigation in state court to those cases that didn’t necessarily end up at trial and to tell the full story of how the cases that did go to trial got there.

It allows you to see judges’ track records on various kinds of motions. When you have a sense of how your judge is likely to rule on a particular type of motion, you can make better decisions for your client on what motions to file and what pitfalls to avoid.

What is the technology behind State Motion Metrics and why is it important?

State Motion Metrics is built around a machine learning-based neural network using the actual orders themselves. State courts use different docketing systems and the docket entry text cannot always give the full picture of what is going on. Often, you can only figure out what happens on a motion by actually reading the order that relates to that particular motion. We built a whole new system that goes through and processes those full documents to figure out what type of motion it was and what happened. With millions of state court cases each year, and often multiple motions within each case, it’s impossible to manually analyze motion outcomes and create a big picture understanding. This allows practitioners access to a whole new category of information that was simply not available in aggregate before.

Lex Machina is very well situated to build such a model, because we have a team of legally trained data experts who can review and code hundreds of motions. After they do that, we can run our neural network on that coding to figure out the relevant factors necessary to determine the outcome from an order, and then run that analysis over millions of documents. We’ve gotten great feedback and lots of excitement from our clients so far.

How has Lex Machina been expanding its state court coverage?

We’re constantly expanding our coverage and rolling out new state courts at a rate of about 12 a year. We first focused on state courts in large commercial centers, like Los Angeles, Atlanta, and New York, and certain counties in major cities, like Harris County in Houston. We have 27 state courts within Lex Machina so far, and we’re continuing to roll out more as we complete the first group. Being acquired by LexisNexis gave us access to all the state data they built up over decades, which will allow us to add more courts at scale.

Can you briefly explain what an API is for those who might not be fully familiar with the concept?

An API allows people to use our data outside of our products, in their own way, through any programming interface they choose. So, for example, it used to be that the only way to access Lex Machina data was to log in to lexmachina.com and use the platform. Over the last five years or so, there’s been a significant acceleration among law firms wanting to make sense of various external data sources in combination with their own internal data. An API makes that possible.

In the case of Lex Machina, users can access our data through our API and integrate it into internal products or internal use cases to mix and match data and make the best of both worlds. The API allows users to access our data wherever they want, outside of our product. 

Why did Lex Machina implement an API for Legal Analytics?

It was in response to our customers asking for the ability to combine our data with other external and internal data sources. Firms and companies are employing more software developers, and the need for an API to help them build their desired tools had hit an inflection point. In certain instances, it also allows companies to export our data and match it up with their internal data.

The API will be able to pull in data from Appellate Analytics very soon. The short-term goal for the API is to cover an increasingly high percentage of all Lex Machina data, so that anything you can do in the product, you can get through the API.

What are some common use cases for your API?

A very common use case for law firms is to have an internal dashboard or other internal tool where attorneys can look up information for a specific judge, for example. The internal page will house all the information the firm knows about that judge from both their internal tracking and experience and the information from Lex Machina.

Another use case is client intake and business development. A firm can consolidate all the information about particular clients, including cases that client had before the firm started representing them and what work they have that the firm isn’t handling. The same information can be pulled in for prospective clients. Using Lex Machina’s API to match our data up with their internal data helps them make data-driven, strategic decisions.

What else can we expect in the future from Lex Machina?

As I mentioned, we want to continue expanding our state court coverage across the U.S. Down the road, we’d also like to potentially expand into international litigation analytics as data becomes more and more available in certain international jurisdictions. 

There’s also the expansion of the API, which is what we’re calling “put Lex Machina everywhere.” Just as companies are interested in mixing and matching our data with their data, we’re interested in being able to do that as well. One of the things that’s nice about being part of LexisNexis is that we have all kinds of different products to pull from. We’d like to be able to add all that information to the litigation record to power even more strategic decision-making.

The acceleration of the legal profession in being more data-driven over the past decade has been exciting, and we want to keep developing new tools and features that push that forward.