{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/01be0d9c78f849d2bf437b6214015f63\" 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/01be0d9c78f849d2bf437b6214015f63-ff79b966a1e33ae1.gif","duration":553.791,"title":"Exploratory Data Analysis Insights","description":"In this video, I walk through my process of conducting exploratory data analysis on a dataset with over 5,000 unique consumer IDs and a fraud ratio of 6.5%. I emphasize the importance of understanding data distributions and the need for feature engineering to identify signals related to fraud. I also highlight key findings, such as the behavior differences between fraudulent and non-fraudulent users. Please review the insights and consider how we can apply these findings to improve our model."}