Refinitiv and the Bank of China team up for AI innovation in FX trading

The Bank of China and Refinitiv have partnered to address the biggest challenges to artificial intelligence application in FX trading. The collaboration will help launch an AI application through Eikon for FX trading signal prediction, utilizing machine power and human knowledge.
Eikon’s open platform allows customers to build their own apps and quickly share FinTech innovations to the global community. Refinitiv’s API also opens access to seamless content integration with the customer’s system, which supports their innovations.

AI innovation in FX trading has been a goal in the field for some time now but it has become a more practical option with progress in big data and machine learning (ML). FX traders are using this progress more and more for predictive analysis.

The Bank of China has over 70 years of experience in FX trading. The bank has utilized deep-learning algorithms to predict the FX price movement for only a couple of years forward, however the Bank’s Digital Asset Management Department has made significant progress.

Here are some of the major challenges in using AI innovation with FX trading:

  • Data: Figuring out what kind of data and data combinations to use in building a FX trading AI model, as well as acquiring high quality data source, also known as ‘feature engineering’.
  • Algorithms: Picking effective ML frameworks and algorithms for different business cases works.
  • Platforms: a platform that can integrate different datasets used in the ML training process, as well as providing enough computation power (GPUs/CPUs) to handle big data.
  • Domain knowledge: FX trader who have deep domain knowledge are necessary to provide market insight and help the machine to use their market experiences in a programmatic way. The data scientist takes the critical role of bridging the gap between technology and business.
AI innovation boosting FX trading in Refinitiv and the Bank of China partnership

The Bank of China and Refinitiv have teamed up to launch DeepFX, a FX price prediction app. DeepFX is an Eikon app that leverages Refinitiv’s data, improving the Bank of China’s Digital Asset Management Department’s FX AI model.

The ‘Liter’ version of the app is free with subscription to Eikon. Traders or FX researchers can use the trading signals the app generates as a reference of short-term trading direction. DeepFX offers improved prediction accuracy and it also predicts the strength of a trading signal to help manage a position.

The FX AI model has integrated trader’s experiences and insights, it has also been trained with a large amount of historical data, aiming to cover as many abnormal conditions as possible so that it can similarly handle extreme market behavior in the future.

A model would be able to behave correctly in Covid-19 pandemic if it has been trained with data from the financial crisis of 2008 or another before that. DeepFx has had a steady performance during the pandemic leveraging broad enough range of historical data for mode training.

DeepFX uses Refinitiv data gathered real-time, historical insights from hundreds of sources and expert partners worldwide, utilizing 25 years of historical tick history data and covering 500 global venues and third-party contributors. The product uses modern API with native Python support to provide consistent access.

Predictive analytics is just one part of the FX trading workflow with many other complex FX business challenges requiring not only AI innovation but many resources. Refinitiv ecosystem provides a combination of available resources.

Read More:

Read Also: