{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/8652ca1268c94649a77295f4041f72ff\" 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/8652ca1268c94649a77295f4041f72ff-29bb3fa5f37855fa.gif","duration":874.772,"title":"Model Evaluation","description":"In this video, I dive into the crucial aspects of model evaluation, focusing on precision and recall curves. I explain how to balance these metrics to optimize fraud detection, aiming for a precision of around 70-80%. I also discuss the financial implications of false positives and false negatives, highlighting a potential loss of $15 million due to misclassifications. Please take a moment to review the calculations and insights I present, as your feedback will be valuable for our next steps."}