AUTHORS

Financial Services are undergoing a rapid digital transformation, pushing banks to allocate more budget towards IT. This shift is driven by Artificial Intelligence (AI) and Automation, reshaping the banking landscape. AI is expected to save banks $447 billion by 2023[1]. This article explores how AI has impacted the credit management process and highlights some success stories leveraging this revolution.

The Credit Management Process

When a customer needs a loan, the financial institution activates a complex process called credit management. This process assesses the applicant’s credit risk. It plays a crucial role in the bank’s ecosystem.

Figure 1

To meet regulatory requirements and reduce risk, banks estimate indicators to provide a clear view of the borrower’s financial health. They use various data points (e.g., borrower’s characteristics) to feed econometric models. These models compute a score of the borrower’s creditworthiness analytically.

Opportunities and Challenges

Traditional credit scoring methods, like logistic regression, are well-established. They offer simplicity and compliance with financial regulations (e.g., GDPR and ECOA). However, these methods struggle with complex situations and non-obvious relationships due to the linearity assumption.

Non-linear Machine Learning algorithms, such as XGBoost, overcome these limits. They discover complex patterns and improve accuracy and robustness. Despite concerns about black-box models, recent improvements and the maturity of AI address these issues. Explainable AI (XAI) and similar techniques allow companies to use advanced algorithms while adhering to ethical principles and regulations like the AI Act. A recent survey[2] suggests that Italian banks agree on implementing an AI Governance Framework to oversee ethical and regulatory issues. Indeed, the most valuable business commodity is trust, especially in the relationship between the bank and the customer.

Enrichment of Credit Scoring Models

The rise of Big Data and AI allows for enriching credit scoring models with new variables. AI models process not only structured data (e.g., balance sheet data) but also unstructured data (e.g., images or text). Banks can now use AI to enhance their credit models with internally generated data, leading to more customizable solutions.

Impact on Banks and Customers

From the lenders perspective:

• Increased Revenue: AI improves risk assessment, enhancing loan quality and increasing revenues.
• Reduced Risk: Accurate risk profiling lowers non-performing exposures (NPE) ratios.
• Operational Efficiency: AI automates processes, reducing operational costs.
• Improved Customer Experience: Faster loan approvals boost customer satisfaction and loyalty.

From the borrowers perspective:

• Credit Inclusion: AI provides more accurate evaluations, offering credit access to previously excluded borrowers.
• Convenient Terms: AI models enable better pricing, including lower interest rates and favorable repayment terms.
• Faster Loan Approval: Automation optimizes response times, giving quicker access to funds.

Challenges and Future Outlook

The adoption of AI in credit management comes with challenges such as bias and lack of transparency. However, AI can enhance the credit process by addressing these issues.

Regulatory Landscape

With the publication of tests for new UK regulations, governments globally are developing regulatory frameworks. Although the UK’s cautious approach contrasts with the EU AI Act, regulation will be crucial for ensuring high-quality data use. It will promote transparency, accountability, and data sharing among organizations.

The recent European AI law addresses quality and responsibility, requiring compliance with risk-based requirements. Organizations should implement internal standards for data accuracy and regularly check for errors.

Figure 2

Open Finance

So far, we have considered the data that banks typically manage or retrieve from information providers. However, the Open Finance circuit promises a broader view. In the future, banks will have access to data on clients’ financial behavior across various institutions. This will foster competition and potentially benefit clients with more specialized and verticalized credit scoring models.

Brazil is leading in Open Finance initiatives. BIP recently conducted an internal Hackathon[3] in collaboration with a major Brazilian market player. Teams developed ideas for loan scoring and propensity scoring, with promising results moving towards commercialization.

AI transforms the credit management process, offering benefits for both banks and customers. It enables more accurate risk assessment and better lending conditions. While challenges exist, AI’s future in credit management is promising, especially with the advancement of Open Finance.

BIP xTech can help

BIP xTech has supported clients worldwide in implementing AI for credit management. Our team of data scientists and credit process experts provides end-to-end support, from vision to deployment. We have successfully delivered over 40 projects, leveraging AI to enhance credit management processes.

Figure 3

Case Study on Credit Card Approval

THE CHALLENGE

An international commercial bank needed to increase the approval rate of retail credit cards without increasing the riskiness of exposures. Previously the bank relied on a linear credit scoring model based on logistic regression to assess customers’ creditworthiness and was seeking a new approach to improve the performance by exploring more advanced statistical models.

OUR SOLUTION

The solution’s objective, released in production and integrated within the bank’s lending process, was to develop an AI model to predict the probability of default of the applicant within the first 12 months. After evaluating several nonlinear ensemble models, XGBoost was identified as the best-performing model.

The data, as well as the processing pipeline in place at the client, were not affected by the proposed solution. Adopting a non-intrusive approach, the task was entirely focused on selecting the best machine learning model without needing any data engineering on the existing information. Hence, the project could be implemented seamlessly and with minimal disruption to the current data infrastructure, maximizing efficiency and ease of use.

The model was trained and validated on a dataset ranging from 2013 to 2016, included more than 100 features and was released in production after eight weeks.

RESULTS

The proposed solution outperformed the previous model significantly and proved itself very stable across all months, leveraging non-linearity and ensemble techniques. It boosted prediction accuracy leading to a simultaneous increase in credit card sales while reducing bad credit ratios. In addition, explainability techniques allowed us to identify the most important variables: average quarterly deposit, number of months of service with the current employer, and monthly income making sure the model was ethically acceptable.

BENEFITS

• +10% credit card acceptance and sales
• -30% defaults incurred within the first 12 months

Conclusions

This article sheds light on how stakeholders involved in the credit process can benefit from AI. Banks can perform a more accurate risk assessment with clear financial gains. On the customer side, these new approaches promote inclusion in the banking system, ensuring that unbanked customers can access the credit market with favourable timing and terms.

As seen from the presented use cases, these technologies can be dropped into current business processes to generate value for both the lender and the borrower.

All disruptive changes generate challenges and opportunities. There are some requirements on the ethical and regulatory levels that must be addressed. AI-powered solutions inextricably link the future of Credit Management, and Open Finance’s advent will further accelerate this. Mitigations mentioned in this article enable harnessing this technology by considering ethical issues as a priority, paving the way for the responsible adoption of AI in the credit industry. BIP xTech can help thanks to relevant experience in AI and specifically in AI-based Credit management related algorithms.

[1] Digalaki, E. 2022. The impact of artificial intelligence in the banking sector & how AI is being used in 2022. https://www.businessin sider.com/ai-in-banking-report?r=US&IR=T

[2] ABI Lab, L’intelligenza artificiale nelle banche, Le nuove sfide, tra strategia e governo, Rapporto AI Hub gennaio 2023

[3] See linkedin post: https://www.linkedin.com/posts/bipbrasil_openfinance-artificialintelligence-businessintelligence-activity-7041518821622345729-sE4d