Applying Behavioural Analytics

Behavioural analytics use machine learning to understand and anticipate behaviours at a granular level across each aspect of the lifecycle of a policy. The information is tracked in profiles that represent the behaviours of each individual, merchant, account and device. These profiles are updated with each transaction, in real time, to compute analytic characteristics that provide informed predictions of future behaviour.

Profiles contain details of monetary and non-monetary transactions. Non-monetary may include a change of address, a request to change beneficiary status or banking details. Monetary transaction details support the development of patterns that may represent an individual’s typical behaviour across multiple industry products – the days when a person tends to lodge a claim, and the time period between geographically dispersed premium payment locations, to name a few examples. Profiles are very powerful as they supply an up-to-date view of activity used to avoid transaction abandonment, caused by frustrating false positives.

Given the sophistication and speed of organized fraud rings, behavioural profiles must be updated with each transaction. This is a key component of helping financial institutions anticipate individual behaviours and execute fraud detection strategies, at scale, which distinguish both legitimate and illicit behaviour changes.

Reshape your claims environment book a chat with, Mouna Eksteen – Executive head, XTND