Credit Kudos launched Signal, a credit score based on Open Banking and machine learning that it says allows lenders to increase acceptance of previously refused customers and reduce defaults.
Singal uses a combination of machine learning and transaction data collected by Open Banking to predict an individual’s likelihood of repayment. The model has been trained on transaction data and loan results collected for over six years and allows lenders to rate all applicants, not just those with a credit history.
The company says lenders can use the system to reach out to currently underserved customers, such as those with thin credit history, new to the country, or bad credit history but now creditworthy.
With increased regulatory oversight of machine learning-based models, Signal has a built-in explainability module, highlighting the five characteristics that contributed the most to a person’s score, helping lenders stay compliant with the rules. transparency and fairness.
The company says a lender using the Signal credit score for those previously declined found it could accept a third of additional applicants, while maintaining its default rate. When used for all decisions, they found that it could reduce overall default rates from 11.7% to 9.7%, while increasing acceptances from 17.5% to 29.8%.
Freddy Kelly, CEO of Credit Kudos, comments: âCredit scores based on traditional credit data are not only limited, but can lead lenders to falsely turn down creditworthy ones. Our new Open Banking-based credit score, Signal, allows lenders to accurately assess all applicants – including those with light records – meaning they can safely increase acceptances without increasing risk or faults. It’s very accurate, fast, and fully explainable, which is an integral part of helping lenders make better, more informed, and more responsible decisions. ”