Boosting the ‘intelligent’ in intelligent payment routing with AI

As Gareth Lodge of Celent said at EBAday 2024, “We're seeing things emerging in smart routing. Not just a set of business rules, but much more dynamic based on pricing and time of day to incentivize customers’ behaviors.” The realization is that, by implementing a few solutions and prioritizing AI in banking, we can now benefit the entire payment chain by bringing innovations to payment routing beyond a basic set of rules.

What is intelligent routing?

For those who have not come across the term, intelligent routing refers to a set of rules that banks use to dynamically direct payment transactions to the most appropriate payment scheme. These rules are based on the paying customer’s preferences, such as cost, timeliness, success rates and other real-time conditions. 

The objective of intelligent routing is to ensure that the transaction is processed using the most appropriate payment scheme, improving transmission efficiency and speed, lowering costs and increasing the likelihood of successful payment completion. The payee also benefits from intelligent routing in terms of cost-efficiency (for example, use of the most favored foreign exchange option), reliability and more.

How does intelligent routing work in financial services?

Intelligent routing routes payments to gateways that historically have better authorization rates for a particular payment type or provides an operating fallback if one payment gateway experiences downtime or fails. In banking, the routing program is trained to choose the best possible path for payments in real time, evaluating the transaction data, scanning system health and applying guardrails when needed.  

How do intelligent routing and AI in banking work together?

While the complex rules currently used in payment routing are efficient, they are manually implemented and relatively static once established. Introducing AI into the payment process has the potential to improve the timeliness and flexibility of routing, as well as enable dynamic consideration of more relevant processing parameters.

Benefits of using AI in intelligent routing: 

• Dynamic adjustments
• Cost analyzation
• Accuracy

Harnessing the power of AI in banking makes intelligent routing more flexible

Using AI in finance enables rules to be dynamically adjusted in real time based on ongoing data, continuously updating which payment gateway is best at any point in time. In addition, by analyzing historical transaction data, AI can predict which payment gateways are more likely to approve a transaction based on factors like geographical regulation, location, time of day and customer behavior.

Utilizing AI in finance makes analyzing transaction costs easier

AI can be used to analyze the total cost of a transaction, including fees related to cross-border payments, currency conversions and interchange rates. AI in finance situations can also help forecast which payment processor will provide the most cost-effective option in any scenario, taking unnecessary burden off customers and employees in the process. 

Using AI in banking situations increases the accuracy of decisions

With AI in finance, the business outcome is accurate and up-to-date routing of each payment through the most efficient payment rail for that payment. This, in turn, improves the customer experience by personalizing routing decisions based on customer preferences and behavior. When it comes to AI in banking, the improvement is ongoing as AI models continuously analyze customer transactions and routing decisions.

4 key strategies for achieving the best outcomes from your AI payment models:

1. Create a PoC
2. Create a sandbox environment 
3. Get access to high-quality data
4. Conduct continuous training and monitoring

Strategy #1: Conduct a PoC to fine-tune models and data

Because AI payment technology continues to rapidly evolve, many of our clients opt to undertake a short proof of concept (PoC) before making a larger investment. These PoCs focus on finding and fine-tuning large language models (LLMs), evaluating the data they access and defining the best prompts (the questions you ask the models). 

Strategy #2: Create a sandbox environment for PoC exploration

Creating a sandbox environment is helpful for exploring the use of AI in banking. To test the PoC and keep your main system safe, you’ll first need to define which features or fixes you aim to test. 

Isolate the network and take backup snapshots after installation and monitor usage to see how your application behaves. If it appears to work, you can move on to the next phases of your AI in finance implementation plan. 

Strategy #3: Ensure access to high-quality, centralized data

Perhaps the most important strategy is data. In banking and payments, AI models require a lot of high-quality data—the better the data, the better the model and its results. In many financial services, this data is dispersed across the banks’ systems, so there may be some work to do to make data available centrally and ensure its quality.

Strategy #4: Conduct ongoing model training and performance monitoring

Once created, AI finance models need to be trained and regularly updated with the latest transaction data. Monitoring model performance in the AI payment solution is critical to ensure they continue to deliver accurate and beneficial results.

Are there any challenges to introducing AI in payment routing and financial services? 

As we might expect, using artificial intelligence to enhance payment routing is not easy due to the sensitive nature of the data and the complexity of AI payment systems. However, these challenges are not prohibitive. We simply need to do the right thing in the right way.

Concerns with implementing AI in banking—and how to fix them:

• Compliance
• Explainability
• Cybersecurity

What kind of regulations affect AI in finance?

First, we need to comply with data regulations (e.g., the General Data Protection Regulation in Europe, the California Consumer Privacy Act in the U.S. and other relevant regulations for your bank’s jurisdictions) by ensuring data is used for its intended purpose. Personal data, especially, should not be collected or retained unlawfully. 

We must also work to avoid discrimination in any AI finance model being used. In the case of AI payment routing, this may be less pertinent than in other areas, such as loan origination, but we still need to ask the right questions to ensure all our customers are treated fairly.

How can AI in banking be more explainable and ethical?

AI systems can be considered "black boxes," making routing decisions difficult to interpret. The European Banking Authority (EBA), the U.S. Federal Reserve and others are increasingly concerned with how AI systems make decisions and whether those decisions can be explained. To stick to ethical guidelines, routing decisions need to be traceable and explainable, especially when issues arise regarding the correctness of an AI payment route or its timing.

What’s the best way to handle cybersecurity issues with AI in finance?

Finally, we should be aware that AI introduces new layers of processing complexity, which increases the risk of technology failure and cyberattacks. It’s important to implement robust risk management and AI systems testing to mitigate these risks.

Exploring the opportunities of AI-driven payments and routing

AI can play a key role in intelligent routing, improving business outcomes for both banks and their customers. While the opportunities for AI payment solutions are promising, careful consideration of the entire ecosystem is required to ensure your business case is neither overly optimistic nor overly pessimistic. 

Connect with CGI to learn more about AI payments

CGI is collaborating with several banks on exciting AI initiatives, and we’re evolving our CGI All Payments solution to leverage this groundbreaking technology. If you’re interested in learning more about our AI payment options and work in banking, feel free to contact me.