Machine learning for risk management and compliance has been driving the adoption of AI-based technology among financial services firms. But as our survey reveals, #MLReadyData is also starting to have an impact in the pursuit of alpha.
- Machine learning for risk management is the main application of AI-based technology, chosen by 84 percent of senior finance personnel in our recent survey.
- Financial institutions are using machine learning to reduce the risk of financial crime by automating complex and costly KYC and AML compliance processes.
- Open source networks are helping to drive innovation and the greater application of machine learning, supported by the availability of high-quality data.
From creating efficiencies to generating alpha, machine learning is already playing a vital role in financial services organizations.
Our recent survey of senior personnel in global finance, including c-suite executives and data scientists, revealed that 90 percent of respondents said they had deployed machine learning in one or more departments.
But how are they applying it — and where is it generating most value?
The number one application cited by survey respondents was risk management, chosen by 84 percent of respondents, well ahead of investment ideas and generation (62 percent). However, that balance is shifting as AI technology matures.
Machine learning for risk management
In a cost conscious, competitive and regulation-driven world, machine learning’s ability to help mitigate losses and prevent regulatory penalties is highly attractive.
By using these technologies to better understand price fluctuations, measure exposure and model how events would impact different investment scenarios, portfolio managers and traders are reducing risk and protecting investments.
Financial institutions are using machine learning to reduce the risk of financial crime by automating complex and costly Know Your Customer and Anti-Money Laundering compliance processes.
From client onboarding and monitoring to investigations, machine learning is being used to search and merge multiple data sources, including adverse media, to better understand the risks associated with an individual or entity.
AI-driven programs can also help address the false positives burden that has increased operational pressures on financial institutions.
Finally, we are seeing the advanced application of machine learning to help identify previously unseen patterns and networks of entities, allowing institutions to be more proactive in financial crime identification and prevention.
Machine learning use is also addressing operational risk by boosting the ability of asset managers and hedge funds to identify weaknesses and improve decision-making processes.
Examples of this include simulating the impact of different geographical and sector exposures, measuring analyst sentiment and modeling different event scenarios.
What these uses all have in common is the ability to generate direct financial benefits in terms of cost savings, asset protection and avoiding the impact of regulatory non-compliance.
Boosting investment returns
When it comes to investment ideas and generation, traders are under increasing pressure to create an edge and so are using machine learning to mine new data sources, identify patterns, search for signals and make predictions in the search for market-beating strategies.
Yet, in terms of deploying these applications in financial markets, barriers still remain. These can be summed up as confidence, explainability and data quality.
With billions of client dollars at stake, moving AI-driven investment strategies from the drawing board to the trading floor can be challenging, with investors needing assurance over the robustness of new models.
One reason is that, in order to be fully backtested and validated, many of these models require deep and reliable data.
Yet in newer industries, such as technology, a company’s data only goes back a few years, posing problems to an analyst studying comparable stocks and past price movements.
Regulators and customers are also concerned about the opaque nature of ‘black box’ models. Adding to this uncertainty are worries over in-built bias and ethical considerations.
That may explain why our survey respondents put investment ideas and generation well behind the use of machine learning for risk management and compliance.
However, we expect this to change as we see regulators and industry collaborate to better understand and address such issues.
One example is recent guidance from the Monetary Authority of Singapore on the responsible use of AI and data analytics for firms offering financial products and services.
Finally, no matter how well built the model, its output will only be as accurate as the data that feeds it. In fact, our survey identified poor data quality and availability as the key challenges to wider machine learning adoption. This is where Refinitiv can help with #MLReadyData.
Driving competitive advantage
As one of the world’s largest providers of financial markets data and infrastructure, we provide the depth and breadth of data required for machine learning deployment.
And we are committed to working in an open and collaborative way with our customers to unlock and create the possibilities that data contains.
Until recently, highly experienced data scientists needed to research and hand build machine learning models from scratch. Now open source frameworks such as TensorFlow, PyTorch and Scikit-learn make it possible to rapidly create and test new models.
This can rapidly drive innovation and application of machine learning, supported by the availability of high-quality data.
At the same time, greater collaboration and transparency will help to address current sticking points. All this should provide fertile ground for the further growth of effective machine learning applications.
We predict that artificial intelligence will be the single greatest enabler of competitive advantage in the financial services sector — and Refinitiv can help you to take full advantage of machine learning for risk and returns.