{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/3b374e0a7cb94456a7008cbdb84b5f77\" frameborder=\"0\" width=\"1728\" height=\"1296\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":1296,"width":1728,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":1296,"thumbnail_width":1728,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/3b374e0a7cb94456a7008cbdb84b5f77-dd907b41c0a241c9.gif","duration":345.25,"title":"Dealership and Sales Forecasting Project Overview","description":"In this video, I discuss my project on dealership and sales forecasting for my DSI course, focusing on the best-selling cars. I've learned about various machine learning models, data engineering, and feature selection through UDA data analysis. One of the main challenges I faced was dealing with heavily cleaned data that didn't reflect real-world scenarios, which led us to introduce synthetic data for better efficiency. I also aim to enhance our model design by incorporating deep learning concepts and building the project in a Docker environment for broader accessibility. I encourage viewers to consider how we can make our project more configurable and professional, moving beyond just notebooks to a more product-oriented approach."}