OCBC pilots AI solutions to detect anomalies found during trading activity audits

OCBC Bank has piloted two artificial intelligence (AI) focused financial technology solutions aimed at beefing up internal controls to safeguard the interests of customers and shareholders, it said on Tuesday.

These solutions aim to improve the detection of anomalies found during the audit of trading activities, and is achieved by analysing trade data using machine learning algorithms.

The two solutions, developed separately by fintech companies - Swedish firm Scila and its French counterpart Cardabel - were among eight that were shortlisted to be part of the 2018 The Open Vault at OCBC (TOV) Innovation Challenge. TOV is OCBC Bank's fintech unit.

Scila's solution involves the development of more than 100 market abuse indicators, which act as a preset list of known anomalies. OCBC said: "Exceptions flagged and investigated can be fed into their supervised machine learning system to refine the market abuse parameters so as to improve the detection of 'true positives'."

Cardabel uses unsupervised machine learning to detect both known and unknown types of trade anomalies. The algorithms do not require preset rules to look for unusual trade patterns that have not been identified previously.

Said Goh Chin Yee, OCBC Bank's head of group audit: "As new risk trends and anomalies continue to emerge for activities in the dynamic global markets, there is a pressing need for us to proactively and accurately identify and respond to them in an efficient and effective way.

"AI has shown an ability to not just analyse huge volumes of data and generate meaningful insights but be a powerful tool in identifying the unknown unknowns in trade anomalies. Through AI, we will be able to further augment our audit effectiveness."

OCBC Bank shares ended S$0.05 or 0.5 per cent lower at S$10.95 on Tuesday.