Legal Analytics should be accurate, complete, and transparent, with sufficient reference to the origins and clear definitions of the terms. This is the only way a legal professional can be confident in the analytics they are using.
Since our origin as a public interest project at Stanford Law School, Lex Machina has been committed to bringing openness and transparency to the law. Every single Lex Machina team member that reviews cases comes from a legal background, so we know that accuracy is paramount in the legal profession. As a team, our goal of prioritizing your trust in using Legal Analytics for data-driven decision making is what sets us above any other litigation analytics provider.
WHY ATTORNEYS TRUST LEX MACHINA
It’s our goal to provide Legal Analytics that always remains accurate, complete, and trustworthy. With Lex Machina, you don’t have to worry about the information gaps or incomplete data that other analytics companies might offer, because our processes ensure that we are the most trusted source of Legal Analytics.
THE DANGER OF “QUICK AND DIRTY” ANALYTICS
When we hear that some of our competitors are packaging “quick and dirty” analytics, we are concerned for the legal professionals that take on the dangerous risk of professional inaccuracy by relying on those analytics. There is only one answer to whether our competitors’ “quick and dirty” analytics are good enough, and the answer is no. It’s irresponsible to provide analytics that are partial or incomplete and claim that an area of law has been covered, as many of our competitors do, because settling for “pretty good” is not good enough for you or your clients. When it comes to Legal Analytics, anything less than the best, most comprehensive data is not good enough because it opens you up to risks caused by inaccuracy.
There are multiple examples of how Lex Machina sits above our competition in terms of striving to earn and keep your trust, including the following:
CLEAN AND ACCURATE DATA
One of the most powerful ways to use Legal Analytics is for attorneys to assess the past experience and track records of their opponents. However, in order to do this effectively, it is critical that the underlying data is clean and accurate.
DOCKET CHALLENGES IN FEDERAL AND STATE COURTS
As a large database that relies on imperfect court records, PACER data understandably contains misspellings of attorney and law firm names. For example, there are over 100 variations of spelling in PACER for the name of one very prominent global law firm. In addition, when attorneys move to a new firm, PACER attributes their past cases to their current firm, which can inaccurately skew perception of a certain firm’s expertise. PACER also does not reliably identify lawyers who work on a case pro hac vice.
State court systems present a different system of challenges. As there is no unified system for state courts, anyone who tries to gather the underlying data to create analytics encounters a myriad of obstacles, including incomplete records, missing judges, and erroneous law firm and attorney data. To further complicate the issue, the inconsistencies vary from state system to state system.
HOW LEX MACHINA SOLVES DOCKET CHALLENGES
Lex Machina uses our patented advanced technology to extract and clean attorney and law firm data on cases, building on the information provided by PACER and state courts, and ensuring accuracy and comprehensiveness. We use our proprietary Signature Block Analyzer technology to add law firms and attorneys to the cases they worked on. Our technology reads the content of the underlying documents – the motions, filings, and orders – to determine which attorneys and law firms were involved in the specific case.
We are proud of our cutting-edge machine learning and natural language processing technology, but we know that to achieve the most accurate outcome, we need to supplement our technology with human review. Our team members bring their specific practice-area expertise and honed understanding of nuanced legal language to ensure that cases are interpreted and processed accurately.
THE RISKS OF RELYING ON OUR COMPETITORS
Unlike Lex Machina, many of our competitors do not add or build on the data collected from the court. Not only do they fail to create comprehensive datasets for their analytics, but when these competitors rely solely on the data provided by the courts without cleaning or normalizing it, they repeat original inaccuracies and errors by omitting crucial cases handled by certain attorneys or law firms whose names are misspelled. They then pass these inaccuracies along to the practicing attorneys who depend on them, running the terrible risk that these attorneys act on inaccurate and misleading information when crafting case strategy or advising their clients. By repackaging docket data without any technological or human review, any competitor opens up their dataset – and the attorneys who rely on them – to significant errors and mistakes.
What the court provides is only the starting point for Lex Machina to build our complete datasets and generate our comprehensive analytics. In contrast, this starting point is where many of our competitors stop.
COMPREHENSIVE AND COMPLETE CASE DATASETS
Lex Machina heavily prioritizes ensuring that our case datasets are complete and comprehensive. We work hard to verify that each case is included in all of the relevant practice areas to which it belongs, via our technology and attorney review, even though the case classifications from the court may originally be incorrect. Not all of our competitors do the same, and packaging an incomplete case dataset as “good enough” is more than insufficient – it introduces risk and inaccuracy into the legal practitioner’s work.
Litigation analytics can grant you the kind of data-driven insights that can tip the scales on your ability to win cases and win business. However, if you are analyzing an incomplete or wrong set of cases, then the “insights” gleaned from that information could actually hinder or even harm your practice.
When we created the Legal Analytics space, we founded it on data integrity. We knew right away that one of our highest priorities always needed to be building a complete data set. This was the only way our customers could safely rely on our Legal Analytics to deliver accurate data-driven insights in their practice and business.
As lawyers and those close to the legal profession, we know that attorneys value knowing the sources of data and information, whether it’s caselaw citations or analytics insights. At Lex Machina, we agree – it’s important to only trust analytics from providers who are willing to show where the analytics came from by providing the underlying case lists and documents, definitions, and navigation search history.
ALWAYS SHOW YOUR WORK
Remember when your third-grade math teacher made you show your work even when you knew the answer to a math problem in your head? The reason your teacher made you show your work is that eventually you’d work on more complicated problems for which showing your work is evidence that you are correct. Legal Analytics is similar. Lex Machina uses sophisticated natural language processing and machine learning technology to build our datasets, clean our data, and generate our Legal Analytics. Then we show our work in order to give you and your clients confidence in our data. That means every analytics datapoint we show in Lex Machina can be traced to the source document or dataset from which it was derived, providing transparency to both you and your clients.
With source documentation, you can quickly determine whether the Legal Analytics can be trusted to be accurate, comprehensive, and based on extractions and review of underlying documents, as it is at Lex Machina.
TRUST AND TRANSPARENCY WITH LEX MACHINA
Lex Machina is proud to have received industry recognition for our dedication to providing transparency. For example, Lex Machina won the 2021 Media Excellence award in the Analytics/ Big Data category for our execution of corporate approach, consumer services, consumer experiences, and content creation. In 2020, Lex Machina was selected as one of the Top 10 Legal Technology Solution Providers by CIO Review for leveraging AI to transform the legal profession and help lawyers provide better service to their clients.
We channel ongoing consideration and thought as to what is included in the help documentation, definitions, and data explanations for our Legal Analytics, and we convey as clear an understanding as possible of our Legal Analytics and the underlying data. We ensure that our state court data and analytics are up to date by maintaining technology that continuously captures and enhances raw data from the state courts. We update cases in as timely a manner as possible and then enhance them by extracting data regarding judges, parties, law firms, and attorneys not found in the basic court data from the docket.
OBSCURITY AND LACK OF INFORMATION FROM OUR COMPETITORS
The fact that our competitors do not offer the same level of transparency and provide readily-verifiable source data is an alarming red flag. You run the risk that they are providing you with analytics that amount to a quick, one-time docket cull that includes the errors and inaccuracies present in the original source data.
When our competitors obscure the source and foundations of their analytics, it is irresponsible, and it makes any attorney relying on those subpar analytics vulnerable to serious professional problems. If you rely on such analytics, you are gambling your important client relationships on unverifiable information.
At Lex Machina, we provide clear source documentation because we strive for transparency, and we are proud of our Legal Analytics. We value the trust our customers have in us. However, there’s another reason, which is that we feel this is the only responsible way to provide Legal Analytics.
Legal Analytics can tip the scales for any attorney, but it needs to be the best, most precise analytics available. As attorneys, we know that you always strive to provide the best, most precise information to your clients. “Pretty good” or “good enough” in the world of litigation analytics is more than merely insufficient – it’s dangerous in a legal profession where accuracy is demanded by your clients and by judges. When you decide on a litigation analytics solution, don’t be swayed by marketing promises of simplicity or low cost. Look for a provider that has done the heavy lifting to clean, structure, and tag the data with technology and human review. Look for a provider who has gone the extra mile to create complete and accurate data sets, to produce insights you can rely on to inform your litigation strategy. Your clients expect you to settle for nothing less.