Nasdaq, Inc. (Nasdaq:NDAQ) has announced it has successfully deployed machine learning technology across its entire Nasdaq Nordic markets-Stockholm, Copenhagen, Helsinki, Iceland-- to bolster its market surveillance efforts.
Nasdaq's SMARTS, in collaboration with the Nasdaq Nordic Market Surveillance team, has implemented machine learning within its surveillance technology to analyze abnormal market events and their subsequent categorization by surveillance analysts across the Nordic markets. The aim of these algorithms is to predict which actions analysts are likely to take based upon their handling of historical activity as well as discover new relationships within the data-thereby strengthening Nasdaq Nordic's surveillance mechanism to detect market abuse. The next stage will be to integrate machine learning technology into the SMARTS offering for exchange and regulator clients worldwide.
"This project marks an important milestone in the use of machine learning in the capital markets," said Tony Sio, Head of Exchange & Regulator Surveillance, Market Technology, Nasdaq. "By closely collaborating with the Nasdaq Nordic surveillance team, we have been able to build unique algorithms that have improved the efficiency and effectiveness of monitoring our own markets. At the same time we are progressing on a broader machine learning strategy and exploring other applications of this technology to strengthen the surveillance process for markets worldwide."
The machine learning capabilities will initially be used to prioritize the surveillance workflow. The technology predicts the likelihood that the event will lead to an action by an analyst. This will particularly help in situations where work load is high, such as during the opening and closing of the markets. The new prioritization ranking is then used to complement traditional quality controls in relation to alert handling, which then enables surveillance officers to identify outliers where the actual handling of alerts has differed from the prediction of the algorithm. Lastly, the existing alert designs will be evaluated based upon new relationships or rules revealed by the machine learning technology and redesigned and improved accordingly.
"This will be one of the earliest applications of machine learning leveraged as an integral part of the surveillance process within the exchange surveillance space," said Joakim Strid, Head of European Surveillance, Nasdaq. "As a market operator, we have always strived to be at the forefront of embracing and applying emerging technologies that will strengthen the integrity of our markets. We look forward to continuing our collaboration with the SMARTS team in further building our machine learning capabilities in our market surveillance endeavours."
As the industry benchmark for real-time and T+1 cross-market surveillance platforms, Nasdaq's SMARTS surveillance technology automates the detection, investigation and analysis of potentially abusive or disorderly trading, to help improve the overall efficiency of the surveillance organization and reduce cost, even as market complexity and new regulations increase. These solutions are used to power monitoring for more than 45 marketplaces, 17 regulators and 140+ market participants, including several buy-side institutions, across 65 countries.