Salon A/B: Optimizing Reject Inference Strategies to Enhance Risk Modeling (TransUnion)

11:25 AM - Thursday, October 09
Salon A/B

Reject inference (RI) is a well-establish feature of sound consumer credit risk models. Beyond fulfilling regulatory compliance requirements, lenders have strong incentives to optimize their RI models, and in doing so, minimize the historical bias embedded in their models on the basis of past credit approval criteria. There are multiple approaches to RI, from rudimentary to highly sophisticated, and this session will discuss best practices and explore alternative methods using updated data science techniques.

Speakers

Chris Scott

Chris Scott
Senior Consultant, Data Science & Analytics, TransUnion

Chris Scott is a senior analytics and statistics professional with deep expertise in multivariate modeling, geospatial analytics, machine learning, and customer segmentation. His work primarily focuses on the lending space, where he collaborates with cross-functional teams to build predictive models, integrate diverse data sources, and enhance decision-making efficiency.

In his current role, Chris advises senior leadership across multiple organizations, helping to identify core business challenges and design data-driven solutions throughout the customer lifecycle. He serves as a strategic bridge between business and technical teams—translating stakeholder needs into analytical frameworks, partnering with data scientists and engineers to transform complex data, and overseeing model development to deliver actionable, high-impact outcomes.