{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/f538e0a02b6941bf8d794d13d3df5f7c\" frameborder=\"0\" width=\"1920\" height=\"1440\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":1440,"width":1920,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":1440,"thumbnail_width":1920,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/f538e0a02b6941bf8d794d13d3df5f7c-974b98611b2195b0.gif","duration":606.761,"title":"End-to-End Credit Scoring and Fraud Detection System Overview 🚀","description":"In this video, I present my risk analysis flagship project, which is an end-to-end credit scoring and fraud detection system featuring daily pipeline monitoring and a web showroom for stakeholders. The demo showcases a 30-day snapshot derived from a Kaggle dataset, highlighting key metrics like average probability of default and flagged fraud percentages. I also explain how the system tracks model performance through MLflow and sends alerts for any significant changes. I encourage you to explore the hosted demo and review the operational guide for a deeper understanding of the system's functionality. Your feedback and insights would be greatly appreciated as we continue to refine this production-style risk system."}