In complex, fast-moving global financial markets, data matters. Applying science and technology to build effective financial prediction models depends heavily on channeling information into a computational system that can rapidly and accurately deliver results.

Aquatic Capital Management (Aquatic Group LLC) manages systematic investment strategies, combining a development platform and sophisticated research with disciplined risk management. Using applied research and artificial intelligence to build investment strategies, Aquatic hopes to build the world’s best prediction machine.

“This company is very much driven by pure scientific research,” said Kevin Weiler (pictured, left), head of infrastructure at Aquatic. “The thesis is that we can do a better job than anyone by applying scientific computation methods. It’s a combination of a lot of different modeling techniques. After we find something that we like as far as a model is concerned, we deploy it, we trade on it and then feed it back into the system.”

Weiler spoke with theCUBE industry analyst Dave Vellante (left) at the Vast presents: Build Beyond event, during an exclusive broadcast on theCUBE, SiliconANGLE Media’s livestreaming studio. He was joined by Jeff Denworth (right), co-founder of Vast Data Inc., and they discussed how Vast’s technology supports Aquatic’s predictive research. (* Disclosure below.)

Synthesized data in unified architecture

Financial trading strategies rely on algorithms that can quickly access large amounts of data to predict and capitalize on market trends. Aquatic turned to Vast and its ability to synthesize structured and unstructured data in a unified architecture that could extract insights from massive datasets.

“What we were talking about was a system that could be standards-based which makes it easy to deploy and manage, a system that could be self-managing in terms of just being like a software appliance,” Denworth said. “What we see is all different types of data now flowing into the system. How do you build infrastructure that can put this all together in one complete picture?”

Meeting that challenge was important to Aquatic, because it relied on frequent iteration of AI models to refine predictive strategies.

“As Aquatic’s businesses evolved, as they’re building these prediction systems, the more different multi-variant data sources that they can assemble, the more accurate that their models can become,” Denworth said.

The Vast DataBase powers native SQL applications and accelerated query engines, such as Spark, Trino and Dremio. This allows researchers to discover correlations over unstructured and structured data to predict and better understand market conditions.

“If you’re training a model and you’re using AI to do that, the most important thing is to be able to do it over and over and over and over again,” Weiler said. “The only way to do that is just to have very, very tight iteration. That was the obvious value add as far as Vast was concerned.”

Here’s the complete video interview, part of SiliconANGLE’s and theCUBE’s coverage of the Vast presents: Build Beyond event:

(* Disclosure: TheCUBE is a paid media partner for the “Vast presents: Build Beyond” event. Neither Vast Data Inc., the sponsor of theCUBE’s event coverage, nor other sponsors have editorial control over content on theCUBE or SiliconANGLE.)

Photo: SiliconANGLE