Predicting legal case outcomes with AI

Predictive AI now helps companies determine whether to litigate or settle, where to file suit, and which attorney to hire.
07.21.22

“Legal decisions are being made today like they were 100 years ago. With AI technology, we can do better than that."–Johnathan Klein, CEO and Founder of Ex Parte.

Every day, companies make critical legal decisions. Do we fight this or settle? Does our patent cover that? Which state should we file in? Litigation is a $250 billion-a-year industry, but legal decisions are often made by following gut feelings.

This process bothered Ex Parte founder Jonathan Klein when he was in law school. The people who were paid to analyze cases really couldn’t factor in all the variables. Later, when Johnathan served as general counsel for MicroStrategy, he noted that more data would have been helpful in making informed decisions. When AI started disrupting other industries, Klein wondered if it was time to change legal analytics for good.


The question that EastBanc Technologies was tapped with was: Could AI predict the probability of winning or losing certain cases based on historical trends and patterns?

Intrigued, we looked at decades of historical case data and recommended a low-risk approach to data analytics, Minimal Viable Prediction (MVP).

Focusing on aninitial data point – one particular type of litigation - we built a predictive analytics engine to test the assumption. With each iteration, we moved closer to answering the legal questions of tomorrow.

“You don’t have to understand the technology to appreciate what Ex Parte can do. EastBanc Tech never questioned if this could be done, they just went to work to solve how to make it happen. When I needed someone with specific expertise for part of our development, they didn’t just give me anyone. They sent a rock star in AI with a Ph.D. in the field, who accelerated our progress."–Johnathan Klein, CEO, and Founder of Ex Parte.

The initial challenge was getting semi-structured court data out of PDF case files into a format that a machine understands. From there, the engine applied machine learning to automate analytical modeling and find hidden patterns and insights within the data. Next, we used deep learning. AI was essential to extract specific information from transactional data, such as case wins, losses, and correlating factors, and then reporting that information contextually to predict outcomes in future patent appeal cases.

“Other fields have been transformed by analytics, but law has been slow to adapt to changes in technology. Better decision-making is a powerful motivator,” says Johnathan Klein. “We anticipate being able to expand Ex Parte’s services to help companies predict the outcome of litigation based on thousands of different variables. In a similar way, law firms could use our service to market themselves based on predicted success rates. EastBanc Tech’s approach is the key to all of that.”


The Ex Parte prototype proved successful. Ex Parte can refine and iterate to add new data sets and test other inquiries for an ongoing stream of actionable, affordable legal predictions. Eventually, the Ex Parte engine can be used to make decisions based on the law firm, lawyer, judge, and other hidden drivers. One day it will offer real-time analytics in cases. The business impact of this technology is significant. Clients who predict the likelihood of success or failure in a case are looking at cost savings of hundreds of thousands or millions of dollars on litigation alone.