{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/7070fcdaabf74ace9cf622e5341107c0\" 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/7070fcdaabf74ace9cf622e5341107c0-4de3fba29d32016c.gif","duration":782.251,"title":"Evaluating Fraud Detection Model Performance","description":"In this video, I discuss how to evaluate the performance of our fraud detection model using precision and recall metrics. I explain the importance of finding the right probability threshold, which I suggest is around 30%, to balance precision and recall effectively. I also calculate the potential monetary savings from the model, which amounts to $194,000 based on our test set of 3,000 records. Please review the calculations and let me know if you have any questions or feedback."}