State Court Litigation Analytics: Enhanced Insights from Lex Machina

Interview with Chuan Qin, Lex Machina Lead Product Manager for State Courts 

Table of Contents 

• What makes enhanced state court analytics in Lex Machina unique? 

• How Lex Machina identifies state court cases that went to trial 

• Why Lex Machina goes beyond court dockets into case filings 

• How Lex Machina captures damages awarded in state court trials 

• Why the ability to verify analytics through case documents matters 

• How Lex Machina “normalizes” law firm data for state court analytics 

• How Lex Machina adds new coverage to enhanced litigation analytics 

State court litigation is notoriously fragmented and opaque. Attorneys often face incomplete records, inconsistent docketing, and limited visibility into outcomes that can make case strategy a guessing game. Lex Machina® changes that. 

With enhanced analytics for civil litigation in over 100 state trial courts, Lex Machina empowers legal professionals to make evidence-based decisions on claim valuation, risk assessment, venue selection, motion strategy, and trial tactics. Our unique blend of advanced technology and human expert review delivers exclusive insights on case timing, motion outcomes, trial resolutions, damages, and more, giving law firms and companies a competitive edge. 

Chuan Qin leads the development of new state-court content and features for Lex Machina, with contributions from engineers and subject-matter experts. In this interview, Chuan shares details about how state trial court case dockets and their filings are collected and tagged within Lex Machina to create the powerful analytics that are only available in our platform.  

What makes enhanced state court analytics in Lex Machina unique? 

We are very thoughtful about how we assemble and structure state court data. To avoid a “garbage in, garbage out” situation, we are very intentional and methodical in the way we take in data from the courts.  This is how we get a clear understanding of what types of data we are assembling and how we count and tabulate analytical endpoints. 

We don’t just pass raw court data to customers. Instead, we enhance and structure it to surface insights that matter—like which judge oversaw trial, which firms and attorneys were involved, and how motions or verdicts resolved. This is especially critical in state courts, where docket information alone often leaves out key players and outcomes. We invest a great deal in processing court data to extract key details about the judges, parties, law firms, and attorneys involved in each case. This is particularly important in state courts, where case dockets alone offer very limited information about the key players involved. Details about attorneys, law firms, or even the presiding judge are not readily available. 

None of the state courts I know of provide a complete record on their case docket for building analytics.  Courts are not in the business of providing analytics.  It is our job to fill in the blanks by procuring the case documents, tagging them for our analytics engine, and extracting details about the key players involved in each case.   

Unlike other providers, Lex Machina not only identifies cases that proceed to trial but also captures what happened at trial including damages awarded, prevailing party, and whether it was a bench ruling or jury verdict. This gives attorneys unmatched visibility into trial outcomes that directly shape case strategy. 

Can you tell us more about how Lex Machina identifies state court cases that went to trial? 

Jurisdictions vary in the types of events they include in the docket to indicate when a trial has taken place. Determining whether a case proceeds to trial solely from docket information is typically less straightforward than it seems, especially for cases that settle after a trial has started. For example, how a trial shows up on the docket in Hamilton County Court of Common Pleas in Ohio can be very different from how a trial gets recorded in the Los Angeles Superior Court’s docketing system.  

We use technology-assisted human review to not only identify when a case is heading to trial but also to confirm that the first call to trial has taken place. This also positions us to determine which judge presided over the trial phase. In some jurisdictions, a single judge may oversee the entire case.  In many state courts, however, a case may involve different judges at various phases of litigation. We invest substantial effort to identify which judge handled the trial phase through rigorous review of court documents, rather than rely solely on automated review of case dockets. 

Are there other reasons that Lex Machina goes beyond court dockets and into case filings for enhanced state court analytics? 

State courts docket their cases according to their own rules, and this leads to significant variance in the metadata associated with filings. For example, in US District Court cases, the docket text for a filing in PACER can reveal whether the filing is an order or a motion, and if it’s a motion, whether it’s a motion for summary judgment, a change of venue, or something else. However, case information from state trial court dockets is specific to the venue and often lacks contextual information about the underlying document and its contents.  

Document-level review is indispensable. Docket text alone often lacks context, especially when judges rule on multiple motions in a single order. By reviewing the actual documents, Lex Machina ensures users get the complete picture of motion outcomes, damages, and final rulings, not just incomplete docket metadata In certain courts, for instance, it is not uncommon for judges to rule on several motions within a single order, and the text of a single docket entry often cannot capture all the pertinent information in a dozen words or less. It’s simply not achievable. You need to review the document to figure out what happened. Document-level review is indispensable to creating analytics that capture the complete picture of motion outcomes, damage awards, and other key details for state court litigation. 

How Lex Machina Goes Beyond the Competition

Trial outcomes: We capture not just whether a case reached trial, but also verdict results and damages.

Judge identification: Our review confirms which judge presided at trial, even when multiple judges are involved.

Human-in-the-loop review: We resolve OCR and handwriting issues that automation alone misses.

Document drill-down: Users can verify insights directly from underlying filings.

Normalized firm data: We unify firm mentions across mergers, splits, and misspellings for true competitive benchmarking.

Information on damages awarded in state court trials is especially important to our customers. Can you tell us more about how Lex Machina captures state-court trial damages? 

We pay special attention to trial resolutions and damages because they were important to the parties if they did not settle pre-trial. When reviewing data for damage awards, our team has encountered numerous instances of handwriting embedded into PDFs, even in today’s digital age, particularly when it comes to verdicts in which jurors record their findings using checkmarks or other hand notations. This is an unsolved problem for OCR (optical character recognition) processes, which is why our human-in-the-loop approach is so important. Our team of analysts, who have legal backgrounds, review the most relevant documents such as judgments or accompanying verdicts to confirm the winning and losing parties as well as any damages awarded. Our team also verifies which judge signed off on the final trial rulings.  
 

Unlike other platforms, Lex Machina gives professionals the inclusive ability to drill down to case documents and verify the analytics themselves. Why is this important?  

It's important that users trust our data. By allowing users to drill down into a case and view the specific documents behind our analytics, we create a win-win situation for both our users and our platform. It supports users' workflows by letting them find related filings alongside the analytics, and it reinforces confidence in the insights we provide. 

How does Lex Machina “normalize” law firm data for enhanced state court analytics? 

We collect the raw mentions of law firms exactly as they appear in the case files or documents and then process them to account for changes over time, such as law firm mergers or splits. Many firm names are often mistyped or recorded with various misspellings, but our system identifies and consolidates these variations to ensure consistency.  

Can you tell us more about how Lex Machina adds new coverage to its enhanced litigation analytics for state courts?  

We believe strongly in building relationships with the courts included within our enhanced state court analytics coverage. We invest considerable time and effort into helping courts understand what we do because we want to be transparent about how we use the court’s case data, and we want to follow their best practices for doing that. It goes without saying, however, that it takes time to build and maintain relationships with court executives and administrators. 

It also comes down to being responsible for the analytics we provide to customers. It takes time and resources to fine-tune our collections process for each court and adapt to any changes courts make to their systems that occur from time to time. We provide customers with full disclosure of what is included in our dataset and are meticulous about our data collection, including specific timeframes and case types.  

Unlike other platforms that may lump case types together in their analytics, Lex Machina allows users to filter and analyze practice areas according to their interests, such as medical malpractice or vehicle torts. Lex Machina’s rigorous approach to data assembly and structuring, and high standards for data integrity are what set us apart from other solutions on the market. 

Ready to turn opaque state court dockets into actionable insights? Discover how Lex Machina’s enhanced analytics can help you anticipate outcomes, benchmark competitors, and craft smarter litigation strategies. 

Sign up for your free Lex Machina demo today and receive a customized litigation analytics report tailored to your practice.