FINRA Uses Deep Learning for Market Manipulation Surveillance

FINRA’s Market Regulation and Technology teams have recently wrapped up an extensive project to migrate the majority of FINRA’s market manipulation surveillance program to using deep learning. 

Susan Tibbs

According to FINRA, this is “perhaps the largest application of artificial intelligence” in the RegTech space to date. 

“What we were looking to do here was really to answer some of the questions that were presented in surveillance: changing market conditions, increased volatility, increased volumes and change in conduct,” Susan Tibbs, Senior VP of Market Manipulation in the Market Regulation Quality of Markets group, said during the “Deep Learning: The Future of the Market Manipulation Surveillance Program” podcast.

She said that using deep learning made a lot of sense to start to answer those challenges. 

C.K. Chow, Principal Developer with the Technology team, explained that deep learning, also known as deep neural network, is a type of technology, which often is said to be inspired by how the human brain works. 

“Essentially, what happens is we have data which flows through a network of neurons. Each neuron has individual weights, which represent the relationship between the input and the output of the neurons,” he said.

Chow added that in the beginning, you have a huge, complicated representation of the market data, but in the end, after they flow through the neurons, it will give you an outcome whether this is of regulatory interest or not. 

“The neuron adjusts its weight, it adjusts how it makes decisions by inspecting a huge amount of market data,” he said.

“We believe that that is a much more robust way of detecting market behavior,” he added.

Tibbs said that FINRA took 11 of its rule-based patterns through this process and came out with eight deep learning models that they are using. 

“We’re certainly looking at the rest of the suite of patterns and where it might make sense to also employ deep learning,” she said.

FINRA processes over 200 billions of market events, said Tibbs, adding that the project was an enormous undertaking.

She added that one of the challenges was just the scale and scope of what they were doing and where to get started and how to take it further. 

“We did a lot of experimentation starting at those first R&Ds. But then even after that to prove out and to refine our concepts,” she said.

Commenting on the technological challenges, Chow said there were three major ones: dealing with large amounts of data; helping the machine to learn how to recognize these cases of interest; and the challenge of testing and monitoring.

The project was going on at the same time that CAT (Consolidated Audit Trail) was being implemented.

Chow said that gave an extra degree of challenge because the CAT data was not mature enough to be used for training.

However, according to Tibbs, with a challenge also comes opportunity: “CAT was really a game changer in that the added granularity and the data is amazing for surveillance,” she said.

According to Tibbs, market surveillance is really essential to maintaining market integrity. 

Deep learning is an “incredibly powerful tool” and helps create better surveillance and definitely the detection and perhaps deterring manipulation and protecting investors, she said.

“It’s definitely not the only tool and great surveillance can be achieved through a variety of different tools,” she added.

“As we get further along in our looking and technology, expand our toolbox, we’re definitely looking at a variety of different approaches. Deep learning just being one of them.”

Tibbs said that advanced technologies are important to continue to improve FINRA’s ability to assess changing market conditions and market conduct. 

“We’re looking at new opportunities to use deep learning and other perhaps more risk-based techniques,” she said.

“We’re presently looking at tools to enhance our clustering ability to identify like and unlike behaviors and how we can use that to enhance surveillance. We have all this amazing data from CAT, and we’re looking forward to continuing to experiment and enhance our ability to really detect and review problematic market activity,” she added.