Nasdaq releases AI tool to better detect malicious activity

Nasdaq has released a new AI-powered tool for surveillance patterns on the The Nasdaq Stock Market to better detect malicious activity.

The solution leverages deep learning technology to better understand complex patterns and hidden relationships within high volumes of data. It can learn invariant representations, and learn any functions including non-linear ones.

Nasdaq vice president and head of marketplace regulatory technology Tony Sio said, “Working closely with our U.S. surveillance team, we are able to train our models based on their experience in monitoring data directly from the trading engine of the world’s most liquid and dynamic market.”

In addition to this, the technology can create new models from old ones with rapid implementation, scalable model development and can detect new forms of financial crime.

To help analysts share their expertise with the technology, it boasts human-in-the-loop learning, ensuring it can be assisted by a member of the team if needed.

The firm is hoping to expand the technology to other exchanges and regulators around the world, as well as other Nasdaq markets. It is also planning to increase the range of scenarios the system detects.

Nasdaq vice president and head of market surveillance Equities Martina Rejsjo said, “The U.S. capital markets are the largest, most liquid financial ecosystem in the world and protecting our markets for retail and institutional investors alike is an important responsibility.

“This means constantly evolving how we adopt and leverage new technologies to better surveil trading activity. By incorporating AI into our monitoring systems, we are sharpening our detection capabilities and broadening our view of market activity to safeguard the integrity of our country’s markets.”

 

Enjoyed the story? 

Subscribe to our weekly RegTech newsletter and get the latest industry news & research

Copyright © 2018 RegTech Analyst

Investors

The following investor(s) were tagged in this article.