Nasdaq invests in artificial intelligence

Stock exchange leverages cognitive computing platform to help detect financial fraud.

Looking to help financial firms more effectively monitor trade activity and prevent potential market abuse, stock exchange operator Nasdaq needed to bolster its surveillance platform to align with the growing complexity of financial crime. It also wanted to create a better standard for monitoring risks that didn't depend on older lexicon search tools, but rather integrated trade surveillance alerts with emerging developments in artificial intelligence (AI).

No hype, just fact: Artificial intelligence in simple business terms

AI has become one of the great, meaningless buzzwords of our time. In this video, the Chief Data Scientist of Dun and Bradstreet explains AI in clear business terms.

Read More

With the help of a cognitive computing platform from Digital Reasoning, Nasdaq is now capable of detecting divulging language in trader communications based on communication patterns. It can analyze data in order to better understand a trader's intentions and actions, thereby exposing potential fraud.

Prior to using the Digital Reasoning technology, Nasdaq had evaluated products for about a year across all the major providers of electronic communication monitoring technology. It determined that the legacy keyword/lexicon-based products were not effective in identifying communications that indicated collusive or manipulative intent and generated excessive false positive alerts, said Michael O'Brien, head of product management, risk, and surveillance solutions at Nasdaq.

The exchange is using the Digital Reasoning platform in conjunction with SMARTS, Nasdaq's own AI-based surveillance technology that monitors for 40 marketplaces, 11 regulator, and 100 market participants across 65 markets globally.

"Both Digital Reasoning and SMARTS are well advanced in bringing together trade and communications data to provide deep context around trading or communication anomalies," O'Brien said. That data feeds into the scoring of alerts so that the highest intensity and risky scenarios can be brought to the attention of analysts.

Nasdaq and Digital Reasoning have a proof-of-concept project underway with a joint bank customer, in which channels have been set up for the passing of information between the two systems. In the first phase of the project communications identified by Digital Reasoning as containing collusive, manipulative, or other anomalous language are being tagged to related trade surveillance alerts in the SMARTS interface.

In this way, the SMARTS analysts can see whether the Digital Reasoning platform has identified unusual communications related to a trader and instrument, O'Brien said. The analysts can then access the communications meta data from within the SMARTS interface, or immediately link back to the full communications within Digital Reasoning's platform.

"This represents a very significant step forward in trade monitoring, as it enables the analyst to have a view of the anomalous trading and the intent of the traders involved in that trading," O'Brien said.

In subsequent phases of the project, SMARTS and Digital Reasoning will enable the generation of alerts or risk flags, which will be generated by taking an integrated view of unusual trading or communications.

"The Digital Reasoning cognitive computing technology is a significant advance on the keyword-based technology that underpins many legacy [electronic communications] monitoring platforms," O'Brien said.

The SMARTS surveillance platform will enable the integration of data and risk flags generated from across multiple surveillance channels, including trade, communications, personal trading, and others. "Machine learning technology will have a significant role to play in the processing of signals from across these diverse channels, so as to flag conduct by an entity which signifies increased risk or potential future risk ," O'Brien said.

Related stories: