OCBC Pilots Two AI Technologies to Increase Anomaly Detection in Trading

Tuesday, 11/09/2018 | 13:06 GMT by Celeste Skinner
  • The solutions were developed separately by Swedish firm Scila and its French counterpart Cardabel.
OCBC Pilots Two AI Technologies to Increase Anomaly Detection in Trading
Bloomberg

Oversea-Chinese Banking Corporation (OCBC) announced today that it has piloted two artificial intelligence (AI) Fintech solutions. The solutions aim to strengthen internal controls to protect the interests of customers and shareholders.

Specifically, the solutions aim to increase the detection of anomalies that are found during the audit of trading activities. It achieves this by analysing trade data using Machine Learning algorithms.

Commenting on the technology, Ms. Goh Chin Yee, OCBC Bank’s head of group audit, said: “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.”

The solutions were developed separately by Swedish firm Scila and its French counterpart Cardabel. The solution from Scila has developed more than 100 market abuse indicators. These 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'.”

Scila and Cardabel were among eight other companies that were shortlisted to be part of the 2018 The Open Vault at OCBC (TOV) Innovation Challenge. This where OCBC Bank’s Fintech unit, TOV, organises an annual challenge that gives selected fintech companies the opportunity to present their solutions to the OCBC community.

AI technology should drastically improve the monitoring process

Cardabel’s solution, on the other hand, applies unsupervised machine learning to known and unknown types of trade anomalies. At the moment, the bank monitors these irregularities through its risk and control units, which conduct daily checks. The Singaporean bank also has internal auditors as a last line of defence.

However, this can be a long process. As such, the bank plans to be able to to make this more efficient with the new AI solutions. In addition to the two solutions mentioned above, as part of the program, OCBC Bank has also completed pilot tests with six other fintech firms - Icekredit (China), Squirro (Switzerland), Lang.ai (Spain), vPhrase (India), EZMCOM (USA), and Ondot (USA).

Oversea-Chinese Banking Corporation (OCBC) announced today that it has piloted two artificial intelligence (AI) Fintech solutions. The solutions aim to strengthen internal controls to protect the interests of customers and shareholders.

Specifically, the solutions aim to increase the detection of anomalies that are found during the audit of trading activities. It achieves this by analysing trade data using Machine Learning algorithms.

Commenting on the technology, Ms. Goh Chin Yee, OCBC Bank’s head of group audit, said: “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.”

The solutions were developed separately by Swedish firm Scila and its French counterpart Cardabel. The solution from Scila has developed more than 100 market abuse indicators. These 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'.”

Scila and Cardabel were among eight other companies that were shortlisted to be part of the 2018 The Open Vault at OCBC (TOV) Innovation Challenge. This where OCBC Bank’s Fintech unit, TOV, organises an annual challenge that gives selected fintech companies the opportunity to present their solutions to the OCBC community.

AI technology should drastically improve the monitoring process

Cardabel’s solution, on the other hand, applies unsupervised machine learning to known and unknown types of trade anomalies. At the moment, the bank monitors these irregularities through its risk and control units, which conduct daily checks. The Singaporean bank also has internal auditors as a last line of defence.

However, this can be a long process. As such, the bank plans to be able to to make this more efficient with the new AI solutions. In addition to the two solutions mentioned above, as part of the program, OCBC Bank has also completed pilot tests with six other fintech firms - Icekredit (China), Squirro (Switzerland), Lang.ai (Spain), vPhrase (India), EZMCOM (USA), and Ondot (USA).

About the Author: Celeste Skinner
Celeste Skinner
  • 2872 Articles
  • 25 Followers

More from the Author

FinTech