Lucas and Luna dive into the hidden bias that plagued credit scoring models for decades—and the data science fix that's finally changing it. They walk through a 2025 study from the Consumer Financial Protection Bureau showing that traditional credit scores systematically under-score borrowers who pay rent on time but lack deep credit history. Using actual FICO and VantageScore data, Lucas explains how proxy variables like 'number of credit inquiries' acted as stand-ins for race and income, and how a new generation of cash-flow underwriting models—using bank transaction data instead of credit bureau records—reduced false rejection rates by 27 percent. They also break down the trade-off: higher approval rates vs. the risk of overfitting to volatile spending patterns. No fluff, just the numbers and the math behind a slow-moving revolution in consumer lending.

#CreditScoring #AlgorithmicBias #ConsumerFinance #FICO #VantageScore #DataScience #MachineLearning #FairLending #CFPB #CashFlowUnderwriting #PredictiveModeling #Technology #TechPodcast #FexingoBusiness #BusinessPodcast #LucasAndLuna #DataDriven #ModelRisk

Keep every episode free: buymeacoffee.com/fexingo