What is the role of litigation analysis in the insurance industry?

A legal staff member pushes a cart with boxes of court documents in front of the U.S. district court in Oakland, California, U.S., on Monday, May 17, 2021. The judge overseeing the high-stakes trial between Epic Games Inc. and Apple Inc. hinted at a compromise that could quell at least some of the game maker's concerns: the ability for app developers to inform users that the iPhone maker's virtual store isn't their only shopping option. Photographer: David Paul Morris/Bloomberg
A legal staff member pushes a cart with boxes of court documents in front of the U.S. district court in Oakland, California, on May 17, 2021.

For decades now the insurance industry has been capitalizing on analytics to understand and predict risk when writing policies. But what if one of those disputed claims becomes a legal matter? Wouldn’t it be prudent for insurers to apply those same kinds of analytics to understand and predict legal exposure?

In the not too distant past, insurance litigation relied almost exclusively on legal research, the expertise of seasoned lawyers and anecdotal data shared among practitioners to prepare for and win cases. Legal research can tell you what legal principles apply in a specific case, but that’s only one piece of the puzzle if you’re trying to learn how the principles were applied.

Using the right advanced technologies, litigation analytics can give you insights into legal cases and trends that were previously unknowable to provide better legal advice, develop better litigation strategies and win more cases.

Data-driven approach
Using litigation analytics, insurance counsel can learn what types of cases have actually been litigated, how long the parties litigated, who represented the opposing parties, what findings the jury or court made, and what damages were awarded. Legal analytics can also provide a detailed litigation history of an opposing party, allowing counsel to understand the party’s strategies and litigation outcomes. By utilizing this information, both in-house counsel and their law firms will be much better equipped to predict how long a case may take, how much it will cost, what damages might be expected, what strategy their opponent might employ, what strategy is likely to be successful, and many other important considerations.

For example, legal analytics for insurance litigation brings data-driven insights to insurance cases pending in Federal District Court from 2009 to the present. The module includes over 144,000 cases (including class actions) involving disputes between an insurer and a policyholder, a beneficiary, or another insurer asserting the rights of a policyholder. It covers a broad spectrum of policy types including home, life, auto, commercial and professional liability, health, disability income, and many more.

These cases all come from PACER (Public Access to Court Electronic Records), a database of several million court documents filed electronically in every District Court case since 2009. By approaching this database with a hybrid process of machine learning to analyze and categorize each case while expert legal analysts annotate the findings made by the court or jury and record damage awards you get incredibly valuable results. This puts a tremendous amount of information at the user’s fingertips: with a few clicks of a mouse, users can gather legal insights that previously could have taken an army of expensive lawyers weeks or months to compile.

Unique policy type differentiation
Good legal analytics will include coding for the most common types of insurance policies, but a word search function can uncover cases involving many other niche policy types which can be analyzed separately, including fire, flood, and cyber security. Policy type codes and keyword searches combined with 50 other case tags covering findings, damages, and remedies, give users the ability to locate and analyze cases involving issues of interest and the relevant type of policy.

This approach to legal analytics gives users easy access to the docket and actual court filings for each case simply by clicking on the case name. Access to the pleadings and rulings allows users to determine what strategies the parties employed in each of these cases, whether those strategies were successful, and how the facts compare to their case. Learning what actually has resulted in successful case outcomes enables lawyers to formulate better litigation strategies.

Another advantage that litigation analytics brings to the table is its ability to conduct detailed research about a particular court or judge. For example, suppose I am counsel in a newly-filed case in the Southern District of New York involving a Commercial General Liability Policy, but my practice is centered in Chicago. When my client asks me for information about the jurisdiction, I can use litigation analytics to locate data for this court and, specifically, cases involving this particular type of insurance policy.

Strategic advantage for insurance counsel
Legal analytics is already the must-have tool to help companies and their counsel make smarter, faster, data-driven business and legal decisions. Certainly, the technology around legal analytics is having a profound impact on the way corporations and their law firms approach the practice of law. All parties in the insurance industry stand to benefit greatly from the use of litigation analytics given the scope and complexity of insurance cases and the breadth of the types of policies available in the market today.

Insurance law firms also will make increasing use of litigation analytics to become better lawyers and new applications for legal analytics in the insurance industry will likely emerge. In the meantime, in an industry that already relies heavily on data and predictive analytics models to assess risk, legal analytics is a welcome addition to the existing toolsets of insurers, insured and their counsel.

For reprint and licensing requests for this article, click here.
Litigation Law and regulation Lawsuits Insurance Artificial intelligence Data Analytics Machine learning
MORE FROM DIGITAL INSURANCE