Shift Technology: AI that understands insurance claims

Shift Technology: AI that understands insurance claims

Written by Roger Peverelli and Reggy de Feniks on 9 Nov, 2017

Paris- based Shift Technology is specialized in insurance fraud detection and claims automation. The company’s SaaS platform leverages Artificial Intelligence, big data and network effects to detect fraudulent claims among its insurance clients. By moving beyond rule-based fraud detection to machine learning, Shift Technology’s efficacy and “hit rate” is more than 2.5 x the industry standard. Given the many challenges insurers face with fraudulent claims and the high costs associated with processing such claims, Shift Technology is able to help its insurance clients drive efficiency and cost savings in their claims management.

Shift Technology is working with some of the world’s leading insurers across the P&C and healthcare sectors in Europe and Asia, and has offices in London, Singapore, Hong Kong and Zurich. It is growing its presence in the United States.

Their ‘secret sauce’ behind their 2.5x better fraud identification rates versus the rest of the market is their ability to combine:

  • In-house R&D based AI and machine learning
  • SaaS delivery model
  • Daily refinement of fraud patterns using data science
  • Financial model based ; clients pay on a per claims basis and being able to end the service any time without penalties.
  • Low implementation costs by connecting to existing processes.


Force for fraud detection
Shift offers a product called Force that uses artificial intelligence (AI) to help insurance fraud specialists better detect behavior that is indicative of fraud. It is an AI and machine learning insurance fraud detection solution delivered in a SaaS model. Force covers all lines of business: Motor, P&C, household, travel, workers compensation, life, and health. With over 100 million P&C claims analyzed and alerts evaluated and classified by fraud handlers, Shift’s AI benefits from a vast data supply and industry expertise rendering Force increasingly powerful over time.
While other fraud analytics offer rudimentary claims scoring, Force goes beyond simple risk provision by providing clear, actionable insights on which indicators make the claim suspect.

The company’s latest Force health Lob solution for health insurance fraud and waste detection solution is already in production with AG2R Mondial. Their Force health LoB solution works in real time across +25 fraud schemes, which is more than a solely human based internal control function will ever be able to handle.

Luke: direct claim settlement
Shift Technology just pre-announced that they will come out with an AI based insurance claims automation solution called Luke in 2018.  Luke opens a new opportunity: direct claim settlement for the insured. By simply uploading their payment statements, they can have the real-time confirmation that it was accepted and that the payment will arrive. From the filing of a claim to the policyholder pay-out, AI will be present every step of the way, reducing end-to-end processing times from weeks to minutes.
The AI module does not require a full recasting of the insurer’s IT system, it can simply be plugged on top of it, thanks to their optimized API implemented by their developers’ team.

This model is also best adapted for an operational use: if it predicts, it can be trusted and thus automates the processing of the claim, otherwise the claim is rerouted to a claim handler. Its performance is therefore naturally measured through two KPIs: its accuracy when it predicts and its prediction rate. Once the concepts are extracted, the module automatically takes the decision to pay and how much based on the parametrized covers and internal handling rules of the insurer. Such an automation amplifies however the risk of fraud. Fortunately, the module uses their Force™ solution for fraud detection, with some specific extensions tailored for claim automation fraudulent behaviors.

On a test set of more than 1M documents, the AI module had a prediction rate of 81% with an accuracy of 97%, even higher than human claim handlers. For a volume of 1M claims per year, this saves a workload worth of $50M and enables to reduce leakage by more than $20M per year.



Why we selected Shift Technology for DIA Munich

Shift Technology is reinventing insurance claims processing with AI. From fraud detection to claim handling.  Each alert that they send helps claims handlers to monitor suspicious behaviors, fight fraud and reduce the claims loss.

Learnings result in savings that could not have been achieved with an insurers ’s own data alone, driving significant network effects. The company has gained considerable traction in the industry with its AI-driven fraud detection technologies. 

Who is Shift Technology?
Paris-based Shift was founded in 2014 by CEO Jeremy Jawish, CSO Eric Sibony, his classmate from Ecole Polytechnique, and CTO David Durrleman. Jeremy and Eric both have technical & mathematics backgrounds and experienced the problem of insurance claims fraud first-hand as analysts within the Fraud Detection department of Paris-based AXA, one of the world’s largest insurance carriers.

Since its founding in 2014, Shift has picked up 45 clients globally, including AG2R La Mondiale in France. Over the past year, the company grew its revenue by 800 percent and doubled its headcount. Key investors: Accel, General Catalyst, Iris, Elaia, Funding raised: Seed funding $1.2M, Series A $10M, Series B $28M (Oct 2017).


Shift Co-Founders (left to right): CSO Eric Sibony, CEO Jérémy Jawish, CTO David Durrleman.

Website: www.shift-technology.com

Presenter 1: Eric Sibony
Presenter 2: Bo Soevsoe Nielsen

Contact info: Stephanie Steel
Email: stephanie.steel@shift-technology.com
Telephone: +33 6 52120291

DIA Newsletter

Stay tuned!

Sign up to always get the latest vision
articles and insurtech news of the Digital
Insurance Agenda.

Subscribe Now
DIA 2017 Munich, 15 and 16 Nov

Secure your seat!

Limited number of October Saver tickets available.

Go to top