{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/79cb485e56d34676a152ce4b49ad4253\" 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/79cb485e56d34676a152ce4b49ad4253-abe69f328e6cf254.gif","duration":356.805,"title":"Model Selection","description":"In this video, I discuss the process of model selection and hyperparameter tuning, specifically using XGBoost for fraud detection. I highlight the importance of parameter tuning and the strategies I employed, such as random grid search and down-sampling techniques to address class imbalance. I also share the AUC results from my experiments, which show improvements in both validation and test sets. Please take a moment to review the findings and let me know your thoughts on the model's performance."}