In a recent episode of the Risk Intel Podcast, Laura Kornhauser, the co-founder and CEO of Stratyfy, shared her insights on the role of Bayesian Improved Surname Geocoding (BISG) in fair lending testing. With her banking background and a passion for responsible artificial intelligence (AI), Laura's journey led her to found Stratyfy, a company dedicated to providing transparent, interpretable, and compliant machine learning solutions for banking. Read, listen or watch the episode below to learn more around this fascinating subject.
Laura explained that fair lending testing is a crucial requirement for lenders, ensuring their lending practices comply with the law and do not discriminate against protected classes. However, for non-mortgage products, collecting racial or ethnic information is prohibited, posing a challenge for fair lending testing. This is where BISG comes into play.
BISG, or Bayesian Improved Surname Geocoding, is an algorithm that infers protected class information based on an applicant's surname and address. It provides probabilities regarding an applicant's race and ethnicity, enabling lenders to conduct fair lending testing without explicitly collecting such information. While BISG is not perfect and has inherent limitations, it is widely used in the industry due to its alignment with regulatory practices.
Stratyfy's Unbias™ solution automates fair lending testing and offers lenders the option to utilize BISG for imputing protected class information, among other capabilities. Leveraging BISG methodology can help improve compliance with fair lending laws and mitigate the risk of discrimination. However, it's essential to recognize that BISG is just the starting point, and further analysis and measurements are required to accurately interpret and act upon its outputs accurately.
Laura acknowledged the complexity of imputation and effectively utilizing BISG's output. Stratyfy has invested considerable effort in developing robust methodologies to translate the probabilistic information into trustworthy measurements. By doing so, lenders can confidently navigate fair lending risk areas and meet the rigorous expectations set by regulators.
The conversation emphasized that fair lending testing, including the use of BISG, is an ongoing requirement for lenders. Regulators are increasingly emphasizing the need for frequent and proactive testing to ensure fair lending compliance. Stratyfy's Unbias™ solution aims to streamline this process, offering lenders the necessary tools to understand and comply with regulations and uphold fair lending principles.
Laura Kornhauser's interview sheds light on the significance of BISG in fair lending testing and Stratyfy's role in helping lenders navigate this complex landscape. By leveraging BISG and implementing robust methodologies, lenders can improve their compliance stance, mitigate risks, and promote fair lending practices.
Contact SRA to learn more about our Fair Lending Assessment or the Stratyfy team who can support you in your efforts to stay compliant around Fair Lending.
Stratyfy works with financial institutions to implement AI and machine learning solutions addressing many critical operations, including automating credit risk assessment, fraud detection, bias mitigation, and other complex tasks without new operational or regulatory risks. Stratyfy's transparent and interpretable solutions help institutions serve more customers by seamlessly combining automated data evaluation with the wisdom of real people to make better, faster, and more equitable decisions.
Follow Stratyfy on Twitter and LinkedIn. For more information, visit http://www.stratyfy.com.
In nec dictum adipiscing pharetra enim etiam scelerisque dolor purus ipsum egestas cursus vulputate arcu egestas ut eu sed mollis consectetur mattis pharetra curabitur et maecenas in mattis fames consectetur ipsum quis risus mauris aliquam ornare nisl purus at ipsum nulla accumsan consectetur vestibulum suspendisse aliquam condimentum scelerisque lacinia pellentesque vestibulum condimentum turpis ligula pharetra dictum sapien facilisis sapien at sagittis et cursus congue.
Convallis pellentesque ullamcorper sapien sed tristique fermentum proin amet quam tincidunt feugiat vitae neque quisque odio ut pellentesque ac mauris eget lectus. Pretium arcu turpis lacus sapien sit at eu sapien duis magna nunc nibh nam non ut nibh ultrices ultrices elementum egestas enim nisl sed cursus pellentesque sit dignissim enim euismod sit et convallis sed pelis viverra quam at nisl sit pharetra enim nisl nec vestibulum posuere in volutpat sed blandit neque risus.
Feugiat vitae neque quisque odio ut pellentesque ac mauris eget lectus. Pretium arcu turpis lacus sapien sit at eu sapien duis magna nunc nibh nam non ut nibh ultrices ultrices elementum egestas enim nisl sed cursus pellentesque sit dignissim enim euismod sit et convallis sed pelis viverra quam at nisl sit pharetra enim nisl nec vestibulum posuere in volutpat sed blandit neque risus.
Feugiat vitae neque quisque odio ut pellentesque ac mauris eget lectus. Pretium arcu turpis lacus sapien sit at eu sapien duis magna nunc nibh nam non ut nibh ultrices ultrices elementum egestas enim nisl sed cursus pellentesque sit dignissim enim euismod sit et convallis sed pelis viverra quam at nisl sit pharetra enim nisl nec vestibulum posuere in volutpat sed blandit neque risus.
Vel etiam vel amet aenean eget in habitasse nunc duis tellus sem turpis risus aliquam ac volutpat tellus eu faucibus ullamcorper.
Sed pretium id nibh id sit felis vitae volutpat volutpat adipiscing at sodales neque lectus mi phasellus commodo at elit suspendisse ornare faucibus lectus purus viverra in nec aliquet commodo et sed sed nisi tempor mi pellentesque arcu viverra pretium duis enim vulputate dignissim etiam ultrices vitae neque urna proin nibh diam turpis augue lacus.