Latest / AI Ethics with Fexingo: Bias, Safety, and Responsible Artificial Intelligence
Why Explainable AI Matters for High-Stakes Decisions
Lucas and Luna explore the growing field of explainable AI, focusing on the tension between model accuracy and interpretability. They use the case of LIME and SHAP in loan approval algorithms, referencing a 2025 study from the Federal Reserve Bank of Philadelphia that found 23% of fintech lending decisions could not be explained by the models' stated factors. The hosts discuss why regulators are pushing for explainability, the trade-offs involved, and how companies like ZestFinance are building inherently interpretable models. They also touch on the EU AI Act's requirement for explainability…
The skinny
The skinny isn't ready yet — notes appear once the transcript is processed.