Nasdaq, for the first time, has brought in A.I. and machine learning to detect any malicious trading.

“By incorporating AI into our monitoring systems, we are sharpening our detection capabilities and broadening our view of market activity,” says Martina Rejsjo.

Martina is VP and Head of Market Surveillance, North America Equities, Nasdaq.  Her objective is to safeguard the integrity of the country’s markets – “the largest, most liquid ecosystem in the world.”

Patterns of market abuse

The usual suspects include unusual price movements, trading errors, and potential manipulation. These generate over 750,000 alerts annually – all reviewed by the Nasdaq’s US markets surveillance team.

Through deploying AI, Nasdaq is also targeting spoofing – another common and undesirable market activity. “We are able to use unique approaches to learn patterns of market abuse, specifically, spoofing, and apply that knowledge to other marketplaces worldwide,” says Michael O’ Rourke. He is Senior VP, Head of Machine Intelligence, Nasdaq.

Nasdaq’s market activity gets an AI shield

The cutting edge, patent-pending technology will incorporate AI capabilities such as deep learning, transfer learning, and human-in-the-loop learning.

Through deep learning computers learn and recognize patterns and hidden relationships by assimilating huge amounts of previous data.

However, transfer learning is the creation of new models from old models.

Human-in-the-loop machine learning is when human and machine intelligence are combined to create effective machine learning algorithms. Human beings participate in both training and testing to improve algorithm results.

The AI functionality was the result of a three-way collaboration between Nasdaq’s Market Technology business, its Machine Intelligence Lab, and its U.S. market surveillance unit.

[Related Story:  This AI-Led Hedge Fund Will Trade Global Currencies ]