JP Morgan pulls plug on deep learning model for FX algos
FX Markets USA: Bank turns to less complex models that are easier to explain to clients
JP Morgan has phased out a model that leverages machine learning technology for foreign exchange algorithmic execution, citing issues with data interpretation and the complexity involved.
The US bank had implemented what it calls a deep neural network for algo execution (DNA), which uses a machine learning framework to optimise order placement and execution styles to minimise market impact.
Launched in 2019, JP Morgan said at the time that the move would replicate reinforcement learning
Only users who have a paid subscription or are part of a corporate subscription are able to print or copy content.
To access these options, along with all other subscription benefits, please contact customer services - www.fx-markets.com/static/contact-us, or view our subscription options here: https://subscriptions.fx-markets.com/subscribe
You are currently unable to print this content. Please contact customer services - www.fx-markets.com/static/contact-us to find out more.
You are currently unable to copy this content. Please contact info@fx-markets.com to find out more.
Copyright Infopro Digital Limited. All rights reserved.
You may share this content using our article tools. Printing this content is for the sole use of the Authorised User (named subscriber), as outlined in our terms and conditions - https://www.infopro-insight.com/terms-conditions/insight-subscriptions/
If you would like to purchase additional rights please email info@fx-markets.com
Copyright Infopro Digital Limited. All rights reserved.
You may share this content using our article tools. Copying this content is for the sole use of the Authorised User (named subscriber), as outlined in our terms and conditions - https://www.infopro-insight.com/terms-conditions/insight-subscriptions/
If you would like to purchase additional rights please email info@fx-markets.com
More on Tech and data
Outlook for e-FX: opportunities and risks for banks
As electronification spreads into new areas of FX trading, banks are under pressure to digitise more of their offerings to remain competitive. The race is now on to automate pricing, trading and hedging in areas such as non-deliverable forwards, swaps…
Why last look needs a new look
Insufficient LP disclosures leave fund managers in the dark on pre-trade costs, says BidFX’s data head
Measuring expected cost models on large FX trades
BestX study assesses factors influencing algo performance on trades over $100m in size
Bloomberg deploys new chatbot tool to Terminal
Offering allows users to surface data and notifications from internal systems without leaving Instant Bloomberg chatrooms
FXPBs see compression tech as key for credit optimisation
FX Markets USA: Providers hope new tech solutions can help replenish credit lines to hedge funds
US insurers take different paths to hedge FX
Counterparty Radar: Maturity and size of FX forwards trades vary significantly between firms
Corporates’ tech stacks face pressure from rising FX volatility
Treasurers and CFOs are worried about how their FX tech will cope with a potential increase in hedging activity
Analyse this: why the buy side is hungry for FX trade data
TCA data from vendors is just the start as buy-side firms enlist quants to analyse execution
