The Commonwealth Bank of Australia implements artificial intelligence technology and machine learning techniques to detect serial abusive behavior in transaction descriptions within the CommBank app and Netbank.
The Australian bank acted last year to ban customers who used transaction description fields from sending abusive messages, including threats to victims of domestic violence.
A bank study, prompted by disturbing messages in the account of a customer experiencing domestic and family violence, found that more than 8,000 customers had received multiple low-value deposits, often less than $ 1, with messages potentially abusive.
The new model was developed in CBA AI Labs and for the first time allows the bank to proactively identify serious cases of abuse. The new tool works in tandem with an automatic block filter that was implemented last year on its digital banking channels to stop transaction descriptions that include threatening language.
Justin Tsuei, Managing Director of Customer Community and Vulnerability, says, âThe new model, which uses advanced AI and machine learning techniques, allows us to deliver a more focused and proactive response than ever before. With this new model in place, not only are we able to proactively detect possible instances of abuse in transaction descriptions, but we can do so on an incredible scale. “
Over a three-month period, from May 1 to July 31, 2021, more than 100,000 transactions were blocked by the bank’s automatic language filter. Of those cases, the new AI tool detected 229 unique senders of potentially serious abuse, which were then manually reviewed to determine the severity and appropriate action required from the bank.
This may include creating new secure accounts for victims and ending banking relationships with abusers.
CommBank is not alone in tackling technology-facilitated abuse. Westpac introduced a new tool in February that allows customers to click a report button within its online and mobile banking platforms to have offensive messages reported and sent to a dedicated team for review and action, which may include notification from the financial institution of the sender of the interaction.
Westpac also uses technology to monitor the language used in outgoing payments, blocking certain transactions containing inappropriate or offensive language in real time.