We are a group of data scientists and legal experts based in Cambridge, UK. We are ambitious and rebellious. We care deeply about our business, our clients, and the future of law.
We started CaseCrunch while students at the University of Cambridge. We profit enormously from a very supportive network within the University and beyond.Learn More
Our systems make accurate predictions about the decisions of judges, ombudsmen and arbitrators. Everything our systems need to make predictions is discoverable before the decision making process starts.
We build lasting solutions for banks, insurance companies, law firms and litigation funders.
We help banks and insurance companies provide a more efficient complaint handling solution to their customers. We also work with law firms to improve litigation strategies based on data-driven analysis of the law and help litigation funders select meritorious claims from their applicant pool.Read more
Based in Cambridge, we are advancing Legal AI everywhere we go.
Our network includes media and industry from many countries and we profit from the financial and intellectual support of the University. We periodically publish tools and research for the community. We have spoken at over a dozen conferences in more than five countries and are frequently featured in technical and mainstream media.Read more
Today's pilots are tomorrow's game-changers.
The architectures we use did not exist four years ago. Deep learning is still a new technology. We are in this business for the long-run. We want to build long-term partnerships and pilot innovative systems to change law one prediction at a time while growing a sustainable business..Read more
Scientific Director Ludwig Bull will travel to Moscow next month to give a talk at the Skolkovo LegalTech conference about how AI helps lawyers identify the factors governing legal decision making.
Marketing Director Rebecca Agliolo will attend the first ever AI and Law Conference in Brazil in November. Her presentation will focus on the importance of research to Legal AI startups and how to deliver value for clients beyond the hype.
CaseCrunch is proud to announce the results of the lawyer challenge. CaseCruncher Alpha scored an accuracy of 86.6%. The lawyers scored an accuracy of 62.3%.
Over 100 commercial London lawyers signed up for the competition and made over 750 predictions over the course of a week in an unsupervised environment.
The problems were real complaints about PPI mis-selling decided and published by the Financial Ombudsman Service under the FOIA.
The main reason for the large winning margin seems to be that the network had a better grasp of the importance of non-legal factors than lawyers.
Evaluating these results is tricky. These results do not mean that machines are generally better at predicting outcomes than human lawyers. These results show that if the question is defined precisely (such as - was this complaint about PPI mis-selling upheld or rejected by the FOS?), machines are able to compete with and sometimes outperform human lawyers.
This experiment also suggests that there may be factors other than legal factors contributing to the outcome of cases. Further research is necessary to establish this proposition beyond the specific parameters of this experiment.
The use case for systems like CaseCruncher Alpha is clear. Legal decision prediction systems like ours can solve legal prediction tasks permanently and reliably.
We are very thankful to the legal community for their enthusiastic participation and to our sponsors for their generous support. We also want to thank our technical judge, Premonition, and our legal judge Dr. Steffek, for their involvment.
A CaseCruncher is a system that makes legal decision predictions. CaseCrunchers are currently available for banks, insurance companies, law firms and litigation funders. Our systems help clients reduce the amount of time and money spent on legal prediction tasks by multiple orders of magnitude, while matching or improving human performance.
Current applications include complaint handling, legal decision forecasting and merits-based claim review.
The first step is to submit an inquiry.
We will make an initial assessment whether our products are suited for your needs. We will set up a meeting to discuss your problem and learn more about your goals. This service is free of charge.
In the second step we will create a detailed project proposal for you.
The project proposal explains how we would solve your problem, what legal and technical difficulties we see, and what the main benefits for you are. The proposal also includes a timeline with clear milestones and an estimated price. We charge a small fee for this step.
In the third step we solve your problem.
We implement the solution and update you on major developments.
Step four is to help you make the best use of your solution.
You can do a lot of things with our solutions. We are here to help integrate the system into your workflow. We also offer maintenance.
As MD, Jozef directs CaseCrunch's strategy and oversees the team. He thinks that CaseCrunch is more than a commercially viable business - it's a startup that is fundamentally challenging legal orthodoxy.
Jozef read law at the University of Cambridge. Prior to joining CaseCrunch, Jozef was the coach of the Slovak national debating team. A debating champion, Jozef serves on the board of the Slovak Debating Association.
Jozef handles business enquiries. You can reach Jozef via email at email@example.com or via mobile at +421 908 893 172.
Rebecca coordinates marketing and client acquisition at CaseCrunch. She believes that Legal AI makes the law more transparent and is relevant to businesses as well as access to justice initiatives.
Rebecca studied law at the University of Cambridge. She has worked on pro bono projects globally and is an expert on human rights law in Subsaharan Africa. She also has experience as a clerk for a New York judge.
Rebecca is the best first point of contact for general enquiries. You can email Rebecca at firstname.lastname@example.org or call her at +44 7540 816817.
As Scientific Director, Ludwig builds deep learning architectures at CaseCrunch. Ludwig's goal is to make language a more perfect means for communication. He is particularly interested in mathematical representations of words as word vectors.
Ludwig read law at the University of Cambridge. He has taken remote courses in artificial intelligence at Stanford University. Ludwig holds a black belt in Aikido and competes in marathons. He also authored a book on the relationship between language and ideology.
Ludwig handles technological enquiries. You can reach Ludwig via email at email@example.com or via mobile at +44 7402 408871.
Make an inquiry below to start the journey to your custom legal AI solution. We will confirm receipt of your inquiry and get back to you with an initial assessment about how our legal AI fits your problem as well as an outline of next steps. Please note that we are not a law firm and do not represent individuals or companies. If you have a legal problem, please consider seeking qualified legal advice.