AI beats lawyers in claims prediction competition

The technology was 86.6% accurate compared to lawyers’ 62.3%

AI beats lawyers in claims prediction competition
Artificial intelligence prevailed over lawyers in a London competition that involved predicting claim outcomes.

CaseCruncher Alpha, which was developed by the same team that created Law Bot, was able to more accurately predict the outcome of payment protection insurance (PPI) mis-selling claims.

The "Lawyer Challenge" attracted 112 lawyers to pre-register for the competition, in which they submitted 775 yes or no predictions whether the Financial Ombudsman would succeed in PPI claims. The participants include lawyers from top firms like Bird & Bird, Kennedys, Weightmans, Allen & Overy, Berwin Leighton Paisner, DLA Piper, DAC Beachcroft, DLA Piper, and more.

After judging by Ian Dodd, UK director of Premonition, and Felix Steffek, senior law lecturer at Cambridge University, the CaseCrunch system came out on top with an accuracy of 86.6%, compared to the lawyers' accuracy of 62.3%.

"We are not necessarily adversaries in this game, the systems like ours can make the legal world more effective for everyone. I am convinced that we have now reached the point where our technology and expertise allow us to satisfy both our vision and our commercial interests. We are looking forward to finding solutions for our clients now," said Jozef Muzak, CaseCrunch managing diretor.

Rebecca Agliolo, CaseCrunch marketing director, said the event was ultimately not about winning or losing.

"It was about showcasing the potential of artificial intelligence and changing the current paradigm not by talking, but by doing," she said. "We hope that the Challenge will be replicated and improved - and we are proud to get the ball rolling."

Ludwig Bull, CaseCrunch scientific director, said that evaluating the 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, machines are able to compete with and sometimes outperform human lawyers. The use case for these systems is clear. Legal decision prediction systems like ours can solve legal bottlenecks within organisations permanently and reliably," he said.


Related stories:
AI will help you meet client needs says law firm report
Australia’s first legaltech major launched

Recent articles & video

Federal Court delivers verdict in Bruce Lehrmann’s defamation suit

KWM pitches in on $3.5bn raising for Kinetic

Media Arts Lawyers partner talks firm's historic appearance in Billboard lawyers list

Baker McKenzie corporate lawyer comes to JWS

G+T acts for Equity Trustees in watershed deal for ScotPac

International Bar Association highlights legal risks from digital twinning projects

Most Read Articles

Hall & Wilcox partner: ‘What we do is tangible’

QIC GC joins HSF as executive counsel

US law firm Weil, Gotshal & Manges to end mainland China operation

DLA Piper helps Indian tech company to boost customer service offering with acquisition