By Scott Dawson
DECTA
Open banking has a lot of potential for growth. Open banking systems were used by 7 million people and businesses in January 2023, according to Open Banking Ltd. research, but this is still a small percentage of the 156 million bank accounts in the UK (see https://tinyurl.com/yvxvsdpz).
Furthermore, while Bud, Plaid and Tink have been successful on their own terms, they can’t compare to the rapid growth of household names like Klarna and Revolut. Open banking also has low awareness and understanding among the general public; some people even question why open banking still exists (see https://tinyurl.com/577f9ssk).
The rise of artificial intelligence (AI) has been talked about in almost every industry this year, including finance. Large language models (LLMs) like ChatGPT may even help open banking to bring it into the mainstream. It could lead to the "killer app" that will make open banking more accessible to the general public—just as MP3 players existed for years before the iPod became hugely successful and in turn spurred the creation of smartphones.
However, unleashing open banking’s full potential with the use of AI will still be a challenging process.
Banks have been required to open their APIs to authorize third parties since the launch of the PSD2 directive in 2018, and hundreds of companies have registered to use open banking protocols in the EU and UK. As of July 2022, 559 third-party providers were registered in Europe, and 221 of them were registered in the UK, reflecting the country’s strong standing in banking and technology (see https://tinyurl.com/kn7tn4rx).
Many of these registrations were either Account Information Service Providers or combined AISPs and Payment Initiation Service Providers. Open banking may be proving its worth more in the provision of innovative financial services rather than being an alternative to card payments at checkouts and ecommerce sites.
As stated by the 7 million figure above, open banking usage is low compared to buy now, pay later services, which are used by 17 million people in the UK (see https://tinyurl.com/57vy8yra). But it has continued to increase and may rise from 15 percent of the public to 44 percent by 2027 if this trajectory continues (see https://tinyurl.com/yy53azmc).
The rise could be attributed to open banking services being integrated into more common processes as opposed to major companies including Klarna. Some consumers signing up for mortgages or loans may use open banking systems for examining their bank account. Many consumers may not even know that an open-banking transaction has taken place; it would just seamlessly integrate into processes that they already use (such as subscription payments).
AI has been prominent in payments and open banking for quite a while, so integrating machine learning and big data into financial services is not new. Even if it is just a sorting algorithm used for basing decisions on customer account information, newly registered AISPs will already use some form of machine learning. The "if X then Y" logic has been used by most basic banking systems, such as the system that sends you a text if you are overdrawn. These could be classed as a form of AI since no humans are making that decision.
In general, AI refers to the common systems that essentially function as flow charts, but when most people are discussing AI today, they're usually referring to the new generation of generative AI pioneered by ChatGPT. These types of machine learning and decision-making algorithms are capable of creating "seemingly new, realistic content" (see tinyurl.com/5984c27y). Therefore, you can ask LLMs to create 10 taglines for a new product launch and it can do so, even producing entirely new content.
For this article, I asked ChatGPT to write a paragraph about the adoption of AI in open banking applications, and it produced the following:
“The adoption of Artificial Intelligence (AI) in Open Banking applications has witnessed remarkable growth, revolutionizing the financial industry. According to a recent study by McKinsey, AI applications in banking have the potential to create $250 billion to $350 billion in value annually. One of the key areas where AI is making an impact is in fraud detection and prevention. A report by Juniper Research predicts that AI-powered systems will save banks over $40 billion in annual fraud-related expenses by 2023. Moreover, AI is transforming customer experience in banking. A survey conducted by Accenture found that 79% of customers are more likely to trust AI-powered recommendations for their banking needs. These statistics highlight the significant role AI is playing in open banking, driving efficiency, enhancing security, and delivering personalized experiences to customers.”
The paragraph generated above demonstrates its current strengths and weaknesses. Although it is grammatically and syntactically correct, it doesn’t address the question, which was specifically about open banking and not banking overall. Furthermore, the three studies cited don’t exist because ChatGPT doesn’t look for evidence to back up its claims when creating an article. Instead it looks at patterns in already existing content and concludes that McKinsey, Juniper Research and Accenture, for example, are the kinds of companies that are cited in articles about the banking industry.
LLMs are not sophisticated enough to undertake the tasks in open banking applications. We already have technology that allows customers to look at bank accounts and see where savings can be made or whether a potential borrower can afford a loan. LLMs can’t be applied to this. AI will likely become advantageous, but LLMs aren’t progressing fast enough to meet the demands of open banking. Although customer services will find it useful, and already use chatbots, generative AI cannot sort fact from language which prevents it from being pushed in the mainstream and used in open banking. 
Scott Dawson, head of sales and strategic partnerships at DECTA, is a highly motivated and results oriented individual with 20 years of experience within the payments industry. Previously, he served as commercial director at Neopay. He has also held fraud management positions at PSI Holdings and Neteller, before becoming senior fraud manager and then business development manager at ClickandBuy, which was acquired by Deutsche Telekom. DECTA provides end-to-end payment infrastructure, from acquiring to issuing and processing, but unlike other players in the crowded payments marketplace the company offers bespoke-as-standard solutions aimed at making payments accessible to everyone. Contact Scott via LinkedIn at linkedin.com/in/scott-dawson-uk.
The Green Sheet Inc. is now a proud affiliate of Bankcard Life, a premier community that provides industry-leading training and resources for payment professionals. Click here for more information.
Notice to readers: These are archived articles. Contact names or information may be out of date. We regret any inconvenience.
Prev Next
