Weightmans Launches Personal Injury Claim Prediction Tool

Weightmans has launched a personal injury claim prediction tool after buying the IP from co-developer Frontier Labs, following an 18-month joint project. The tool, MatterLab, can boost the accuracy of personal injury ‘reserve’ cost predictions by 20%, the firm said.

The UK law firm received a taxpayer-funded grant worth £165,800 ($226,000) from Innovate UK to start the project. Weightmans’ Innovation and Data Science teams spearheaded the project.

MatterLab is focused on what is called ‘reserving’, a key part of handling the financial aspects of a personal injury lawyer.

According to Investopedia: ‘A claims reserve is a reserve of money that is set aside by an insurance company in order to pay policyholders who have filed or are expected to file legitimate claims on their policies. Insurers use the fund to pay out incurred claims that have yet to be settled.’

As Will Quinn, a partner at Weightmans, explained: ‘Reserving is one of the most business-critical stages when handling personal injury claims – it can impact everything from loss forecast estimates, insurers’ solvency and customers’ reinsurance premiums.

The challenge is that reserving often takes place in a knowledge vacuum, with individual case handlers often having to work with minimal detail and only their previous experience to draw on. 

‘We knew that AI-enabled technology and predictive analytics tools were key to complementing the capabilities of case handlers, ensuring they have as much data as possible at their fingertips to boost the accuracy of their calculations. This investment represents our commitment to augmenting the specialist skills of handlers to help them provide the most accurate, insight-driven results for clients.’

MatterLab uses historic claims data to create a model that enables case handlers to more accurately reserve at a much earlier stage in the claim, often when important claims information is still outstanding, the firm added. If you want some personal assistance, get it here from the Tingeys workmen comp attorneys.

Under initial closed pilots, the tool was shown to boost the accuracy of reserve predictions by 20%, ‘significantly reducing the amount of over and under-reserving on an individual case by case basis’.

Clearly the more cases you handle the more this capability adds value for the client….and insurance companies face a huge volume of claims.

The new initiative follows the previous launch of PREDiCT Large Loss, also developed by Weightmans’ inhouse data scientists, which uses a similar methodology ‘but with a far more granular data set, to support large loss claims handlers in reserve calculations. Its pilot testing delivered a 71% improvement in reserving accuracy’. In this scenario they reckon they can reduce reserves by £285,000 ($388,000) per case.

MatterLab will be rebranded to sit alongside the suite of tools that Weightmans has developed under the PREDiCT banner, the firm said.

Stuart Whittle, Business Services and Innovation Director, concluded: ‘This is an exciting development for Weightmans and demonstrates our commitment to invest heavily in new technologies and innovation that will support our people to deliver the very best results for our clients. Using data-led insights to transform our claims handling capabilities is key to our service delivery by helping our clients manage their financial liabilities and drive down overall indemnity spend.’

Steven Hassall, Design Director of Frontier Labs, added: ‘It has been a pleasure working alongside Weightmans to design and develop MatterLab. We are very proud of what has been achieved so far and wish Weightmans the best of success commercialising the product.’

All in all a great example of a law firm leveraging data to create a tool that creates substantive value for the clients, in this case insurance companies. It’s also an example of where a taxpayer-funded grant for legal tech has resulted in a genuinely useful product.

Be the first to comment

Leave a Reply

Your email address will not be published.


*