Detection of Abuse in Financial Transaction Descriptions Using Machine Learning
This addresses a critical safety issue for banking customers, particularly victims of domestic violence, by detecting abuse in a new digital channel, though it is an incremental application of existing NLP methods to a specific domain.
The paper tackles the problem of tech-assisted domestic and family violence through abusive messages in financial transaction descriptions, resulting in a deep learning-based system that identifies high-risk abuse cases by scoring millions of transaction records.
Since introducing changes to the New Payments Platform (NPP) to include longer messages as payment descriptions, it has been identified that people are now using it for communication, and in some cases, the system was being used as a targeted form of domestic and family violence. This type of tech-assisted abuse poses new challenges in terms of identification, actions and approaches to rectify this behaviour. Commonwealth Bank of Australia's Artificial Intelligence Labs team (CBA AI Labs) has developed a new system using advances in deep learning models for natural language processing (NLP) to create a powerful abuse detector that periodically scores all the transactions, and identifies cases of high-risk abuse in millions of records. In this paper, we describe the problem of tech-assisted abuse in the context of banking services, outline the developed model and its performance, and the operating framework more broadly.