AI for insurance claims fraud detection

Jubilee Holdings, an insurer listed in Nairobi that operates in Kenya, Uganda, Tanzania and Burundi, disclosed in its 2025 annual report that it averted Sh1.28 billion in fictitious insurance claims during the year, of which Sh750 million was identified through AI driven claims adjudication and analytics based fraud detection tools rather than other controls. The insurer said it deployed Curacel, an AI enabled system that supports clinical claims adjudication, and that an AI supported fraud detection tool helped it identify and act on 449 suspicious cases during the year, up from the previous year.

Lemonade's claims bot AI Jim takes the first notice of loss in a chat with the customer, pays or declines simple claims within seconds and assigns the claims it may not settle, or has concerns about, to human claims experts based on their specialty, workload and schedule. A separate system, Forensic Graph, uses machine learning to predict, detect and block fraud across the customer engagement. The annual report states that AI Jim took the first notice of loss without human intervention 96% of the time and that roughly 55% of claims were automated from start to finish, both as of December 31, 2025.

Old Mutual General Insurance's managing director in Kenya, Japheth Ogalloh, told Business Daily Africa that the insurer's investment in AI helped it save almost Sh400 million in 2025 by streamlining routine tasks and flagging fictitious claims. He said the company relies on AI to reduce revenue leakage and detect fraud patterns, and that AI cuts paperwork in claims management by analysing patterns in claim forms, which also sped up the claims process for customers.

In 2023 Gjensidige took new technology into use to uncover insurance fraud. In an interview on Gjensidige's own site, Vera Sønsthagen, head of investigation, says the technology covers 100 different parameters that analyse and assess images and documents from claims, for example whether the date a photo was taken matches the phone's iOS update and whether the geolocation matches where the person says something was lost, looking at both metadata and visual content.

Separately, investigators use a so called SVIK filter that analyses internal and external data sources, including the content of the claim notification, and gives a score from 0 to 100 for the likelihood of fraud. She says investigators also use AI tools to analyse and summarise text and to evaluate images, and that human judgement is still needed for nuance and context. No quantified outcome is disclosed.

Covéa, described in the announcement as a UK insurer, selected Shift Technology as a long term strategic partner to replace fragmented fraud tools with one platform spanning underwriting, claims and mid term policy adjustments. The AI supports underwriting risk analysis, claims fraud detection, compliance risk scoring and case management, aiming at a consistent view of risk from policy inception through to claims settlement. Covéa reports that the underwriting component of the deployment delivered a return on investment within three months of going live, driven by earlier risk identification and reduced leakage.

GNP Seguros (Grupo Nacional Provincial), Mexico's largest insurer, uses Palantir's Foundry and Artificial Intelligence Platform (AIP) in production to detect claims fraud, monitor risk and support underwriting decisions. GNP is scaling the deployment across its health, life, auto and damage insurance portfolios to unify claims, underwriting, operations and risk data on one platform, so anomalous claims patterns and potential fraud can be flagged before a claim is paid. Palantir named GNP Seguros as its first publicly announced commercial customer in Latin America.

Shelter Insurance has implemented Shift Technology's Shift Claims Fraud Detection tool to strengthen its defences against auto and property insurance fraud. The tool gives the special investigations unit contextual information and documentation on each claim, so the team can identify a greater number of suspicious claims, separate them from legitimate ones, and investigate and conclude cases quickly, accurately and fairly. No quantified detection or loss figures are disclosed.

Tokio Marine & Nichido Fire Insurance uses Shift Technology's claims intake and claims fraud detection solutions, extended with generative AI that extracts data from structured and unstructured sources such as images and documents. The system highlights the points handlers should check for consistency across estimates, damage photos and claim statements, which makes reviews more efficient and more standardized, including during the surge of claims after large disasters, and it helps detect suspicious claims, which tend to rise after such events. No figures were published.

AXA Switzerland checks motor and property claims for fraud in real time at first notice of loss with Shift Claims Fraud Detection, using more than 100 fraud scenarios tuned to the Swiss market and its portfolio, and combining its own policy and claims data with external sources such as government records. Honest claims go straight to processing, suspicious ones go to an expert with the full context of the alert, and the models run again whenever new data is recorded on a claim. Shift reports that AXA has analysed more than 1 million claims and stopped over EUR 12 million in fraud.

Assurant has used Shift Claims Fraud Detection since 2018 to flag suspicious claims to its special investigations unit, after a trial in which the system identified dozens of fraud cases. Alerts carry the context investigators need, the investigation software was adapted to the unit's workflow, and the models were refined for schemes involving specialty vehicles, extreme weather and multiple claims. Shift reports that the unit's case acceptance rate rose over four years, leading to more fraud mitigated, but gives no figures.

Tawuniya, which the release calls the pioneering insurance company in Saudi Arabia, partnered with SAS to bring an end to end Insurance Fraud Management system into its health insurance line of business. The system applies SAS predictive modelling and machine learning to detect anomalies and outliers across medical claims, aiming to speed up claims settlement and fraud identification, reduce false positives for investigators and give them documented analytical evidence for each flagged case. Tawuniya's CEO framed it as part of the insurer's wider digital transformation programme.

Member insurers of the General Insurance Association of Singapore analyse travel and motor claims together with Shift Technology's AI, which finds connections between people, providers and claims that look genuine when each insurer sees them alone. The data analytics initiative started in 2017 with 25 insurers; fraud alerts are issued to members and prompt joint investigations. The public page gives no outcome figures.