Katana gives bond traders a cutting edge
12 December 2017
ING is harnessing the power of artificial intelligence to help bond traders make faster and sharper pricing decisions with a new tool called Katana. Named after the ultra-sharp Samurai sword, Katana uses predictive analytics to help traders decide what price to quote when buying and selling bonds for their clients, based on historic and real-time data.
Santiago Braje, global head of
Credit Trading
Katana learns from the history of hundreds of thousands of trades and translates this into a prediction or suggested decision for the trader. By organising and displaying these predictions alongside relevant data in a way that can be intuitively absorbed by the trader, it is uniquely designed to complement the trader’s own decision-making, not replace the trader.
“We have seen some examples of applied AI on the trading floor before, but in most cases they have a narrow focus on automation,” said Santiago Braje, global head of Credit Trading. “This restricts them to liquid asset classes where the trader is replaced by a machine.”
Man and machine
The key advantage of Katana is that it is designed to enhance cooperation between man and machine.
It graphically presents the most useful information the trader can process it more effectively, which leads to faster and more accurate pricing.
“With Katana, AI is applied to enhance the traders’ decision-making abilities, allowing them to use their natural intuition and expertise in the most effective way. This is a powerful combination,” said Santiago.
“Our traders stay fully in control, but are now better equipped to give the best quote to our clients every time.”
The first results of testing Katana with the emerging markets (EM) desk in London show faster pricing decisions for 90% of trades; reduction in trading cost by 25%; and traders are able to offer clients the best price four times more frequently.
Katana is the result of intensive research and development by ING’s Financial Markets Global Credit Trading team in London and the Wholesale Banking Advanced Analytics team, who will continue to collaborate on new functionalities to update the tool and further improve traders’ performance.
