Traders and AI scientists at RBC and Borealis AI collaborate to deliver a real-world AI solution to help improve trading results and insights for clients in a measurable and explainable way

TORONTO, October 14, 2020 – RBC Capital Markets today announced the launch of Aiden^®, an AI-based electronic trading platform that uses the computational power of deep reinforcement learning in its pursuit of improved trading results and insights for clients.

The Aiden^® platform was developed jointly by RBC Capital Markets and Borealis AI, a world-class AI research center created by RBC, as traders and AI scientists worked side-by-side to create the initial bold concept and deliver a real-world solution. In doing so, both organizations undertook one of the biggest challenges in the field of AI today – applying deep reinforcement learning into a constantly changing environment like equities trading, with measurable and explainable results for its users.

“Aiden^® speaks to our long-term commitment to leverage next-generation AI technology to create differentiated solutions for our clients,” Bobby Grubert, Co-Head of Global Equities‎, RBC Capital Markets, said. “Aiden^® is the result of a massive collaborative effort between RBC employees, including traders and AI scientists, and our partners at Borealis AI. Aiden^® is at the beginning of its journey and we see great potential to further expand its capabilities and redefine execution, while remaining true to its client-centric foundation.”

“After several years of comprehensive research, testing and fine-tuning, we are proud to bring a new standard of execution excellence to clients,” Dr. Foteini Agrafioti, Chief Science Officer at RBC and Head of Borealis AI, said. “Together, we are continuing our exploration of deep reinforcement learning, while advancing the development of responsible AI for our clients.”

The Aiden^® platform has shown the ability to navigate the challenges of fluid and dynamic market conditions in real-time, without the need for continuous re-coding like traditional trading algorithms. Utilizing hundreds of pre-programmed data inputs and its ability to make more than 32 million calculations per order, the Aiden^® platform is able to execute trading decisions based on live market data, dynamically adjust to new information and learn from each of its previous actions.

“The market volatility we have seen during COVID-19 has been a great proving ground for Aiden^®,” Shary Mudassir, Co-Head of Global Equities Execution, RBC Capital Markets, said. “Aiden^® was able to recognize the sudden changes in the market and adapt to them, allowing it to preserve performance. The Aiden^®platform is part of our vision to be one of the best in the world at unlocking the potential of Artificial Intelligence and delivering those insights to our clients in an explainable way.”

The first live Aiden^® solution, a volume-weighted average price (VWAP) algorithm, was designed to help improve clients’ trading performance by reducing slippage – the difference between the expected price of a trade and the price at which the trade is executed.

“The Aiden^® VWAP algorithm has demonstrated, under a standardized evaluation framework used to eliminate bias, the ability to significantly reduce slippage against market VWAP in the U.S. equity market,” Jas Sandhu, Head of Equities Algorithmic Trading, RBC Capital Markets, said. “There are plans to expand the Aiden^® application to RBC Capital Markets’ full suite of electronic trading algorithms.”

The Aiden^® platform is currently available to RBC Capital Markets clients who are trading in U.S. and Canadian equities, and there are plans to introduce the platform to additional clients across its geographical markets in the coming months.

The Aiden^® platform follows in the footsteps of a similar trading innovation introduced by RBC Capital Markets in 2011 called THOR, a smart-order-routing technology that helped address the problem of disappearing liquidity and assisted clients with competing with High Frequency Traders.

“Aiden^® continues our track record of working with our clients to better understand and address their key challenges and create value through innovation in a responsible and transparent way,” Grubert added. “Today’s Aiden^®announcement is just the first step in what we believe will be additional possibilities for how we can expand the application of artificial intelligence to trading intelligence for our clients.”