Credit Kudos, the Open Banking credit reference agency, has introduced Signal, which aims to serve as an accurate, explainable Open Banking credit score in order to assist lenders with serving the requirements of more clients, lower defaults and evidence risk decisions.
Currently available in the market, the score allows lenders to move beyond the existing limitations of conventional credit data, enabling them to reliably score applicants, not just those consumers with established credit histories.
Signal has been developed to allow lenders to accurately predict risk by leveraging highly relevant and up-to-date financial behavior data, and by using machine learning algorithms with clear explainability. This helps lenders with understanding the motive for compliance purposes and the risk profile of their target population.
Signal reportedly makes use of machine learning and Open Banking-collected transaction details to predict an individual borrower’s likelihood of making timely repayments. The innovative model has been trained on transaction data and loan outcomes, accumulated for over 6 years. The model has been designed to make sure the data is quite accurate and a lot more detailed than what lenders have access to via conventional credit data.
The main benefits are as follows:
- Increase acceptances: With a highly accurate understanding of anyone’s financial situation, lenders can reach currently underserved customers. This includes those who have a thin credit file, are new to the country, or who have adverse credit history but are now creditworthy – which Credit Kudos estimates to be around six million.
- Reduce defaults: Signal leverages Open Banking data and insights to accurately predict someone’s creditworthiness. Using machine learning trained on more than six years of data, lenders can assess people more accurately than with traditional credit scores, which reduces the likelihood of a borrower defaulting.
- Understand and evidence risk decisions: The Open Banking credit score has clear explainability so lenders can understand and evidence the decisions driven by machine learning, allowing them to fulfill regulatory requirements around transparency and fairness. It does this by surfacing the five features that most contributed to the person’s score.
One lender leveraging the Signal credit score for those previously declined revealed that it was able to accept a third or over 30% more applicants, while being able to maintain its default rate – indicating that there was no extra risk to handling more applicants that they could have been rejected based on non-Open Banking credit scores.
When used for key decisions, they determined that it would lower default rates from 11.7% to 9.7%, while boosting acceptance rates from 17.5% to 29.8%.
Freddy Kelly, CEO of Credit Kudos, stated:
“Credit scores based on traditional credit data is not only limited but can lead to lenders wrongly declining those who are creditworthy. Our new Open Banking-powered credit score, Signal, allows lenders to accurately assess all applicants – including those with thin files – meaning they can safely increase acceptances without increasing risk or defaults. It is highly accurate, fast, and wholly explainable, all of which are integral features to helping lenders make better, more informed and responsible decisions.”