UBS targets FX liquidity traps with machine learning
(14 May 2019 - Europe) Swiss bank UBS is utilising machine learning technology to carry on dealing foreign exchange (FX) during 'flash crashes' triggered by shutdowns in algorithmic trading systems when volatility spikes.
While algorithmic trading represents an expanding element in the US$5.1 trillion-a-day global FX market, accounting for up to one in five trades and up to 70 percent of all orders placed on multi-dealer currency platform EBS, machine learning is still relatively new.
UBS is the fastest-growing FX algo broker by market share from Q2 to Q4 2018 according to Boston Consulting Group (BCG) and Expand, a benchmarking house for financial institutions. UBS is not the only global lender investing significant resources in 'algo' technology as it cuts back on trading staff headcount and relies more on automatically computed strategies to execute FX trades more efficiently. JPMorgan has released a new machine learning algorithm and Citigroup is another major global player in digital currency trading.
UBS's optimal routing control algorithm (ORCA) machine learning system enables the algorithm to determine within microseconds the best platforms and execution sequence to use, estimating the probability of trading and market impact for each specific order and reducing costs for the group's clients. That can be crucial in a fragmented global FX market, where over 70 different platforms exist with multiple banks, hedge funds and technology firms competing for market share. The growing number of 'flash crashes' also complicates matters. While Q1 2019 figures are not yet available for algorithmic trading performance, UBS said growth has continued this year. The bank expanded ORCA to US Treasury trading in late 2018, with further roll-outs expected in the Foreign Exchanges, Rates and Credit (FRC) space.
“What is unique about ORCA is the machine learning we put into it. Clients can see their executions improving, they can see their fill rates improving. We’ve learned along way there’s a sort of science of innovation. You can teach people to be better at innovation" said UBS FRC Strategic Development Lab Head Chris Purves. “The way forward for everybody is to build a platform where you’re going to be able to serve a much wider group of clients at a very low margin of cost per new client" stated UBS Investment Bank COO Beatriz Martín Jiménez. "Banks have traditionally focused on premium clients but new digital technologies would allow access to a broader customer base."