RBC Capital Markets has launched a new electronic trading platform using artificial intelligence technology, which was developed by its traders in partnership with AI scientists.
Known as Aiden, the platform uses deep reinforcement learning processes to adapt to changing market environments and execute trading decisions based on live market data.
Aiden uses pre-programmed data inputs and can make more than 32 million calculations per order without the need for re-coding like traditional algorithms.
Shary Mudassir, co-head of global equities execution at RBC Capital Markets, stated that the market volatility seen during ongoing coronavirus pandemic has provided the firm with an opportunity to prove its ability.
“Aiden was able to recognise the sudden changes in the market and adapt to them, allowing it to preserve performance,” Mudassir added. “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.”
RBC Capital Markets said its traders worked alongside AI scientists at its Borealis AI research centre to create the initial concept and develop the platform. A volume-weighted average price (VWAP) algorithm was the first Aiden solution to go live, allowing reduced slippage to improve the broker-dealer’s clients trading performance.
“The Aiden VWAP algorithm has demonstrated, under a standardised evaluation framework used to eliminate bias, the ability to significantly reduce slippage against market VWAP in the US equity market,” said Jas Sandhu, head of equities algorithmic trading at RBC Capital Markets. “There are plans to expand the Aiden application to RBC Capital Markets’ full suite of electronic trading algorithms.”
Aiden is available to RBC Capital Markets clients that are trading US and Canadian equities, with plans to roll out the platform to other clients across its geographical footprint in the coming months.