Beyond Defensive Reporting: Machine Learning for Active Anti-Money Laundering Control in Insurance
2026-06-15 • Machine Learning
Machine Learning
AI summaryⓘ
The authors studied how machine learning can help insurance companies spot suspicious claims that might be used for money laundering before any money is paid out. They used data from a Norwegian insurer and taught a model to recognize patterns in claims that were later flagged for laundering. They also found that including information about insurance fraud helped the model detect laundering better. Their best model was able to catch about two-thirds of laundering cases by reviewing only a small percentage of claims. This is the first study to use machine learning specifically for detecting money laundering in insurance claims.
money launderinginsurance claimsmachine learninggradient-boosted decision treesfraud detectionbehavioral patternsBudget-Weighted Capture Ratemodel trainingfraud labelsclaims investigation
Authors
Dara Goldar, Geir Kjetil Ferkingstad Sandve, Martin Jullum
Abstract
Money laundering through insurance claims poses a threat to insurers both through fraudulent payouts and reputational and regulatory risk. Despite this, little research has examined how such laundering can be prevented. This paper examines whether machine learning can help insurers flag suspicious claims before payout, shifting the focus from passive reporting to active prevention. Using production data from a major Norwegian insurer, we train gradient-boosted decision tree models to detect claims later reported to authorities for suspected money laundering. Because fraud and laundering may share behavioural patterns, we also examine whether insurance fraud labels can serve as an auxiliary training signal. We compare different learning setups using the Budget-Weighted Capture Rate, a metric introduced in this paper to measure how many laundering cases are captured when only a small share of claims can be manually reviewed. The results show that incorporating fraud-related investigation labels substantially improves laundering detection. The best-performing model captures nearly two-thirds of laundering cases within the top-ranked 2 to 6 percent of claims selected for investigation. To our knowledge, this is the first empirical study of machine learning for money laundering detection in insurance claims.