{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/951764f8f44f42a8b56aaf4fe1f4a569\" 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/951764f8f44f42a8b56aaf4fe1f4a569-ec3db64cbc2bac35.gif","duration":238.68,"title":"Car Sales Forecast Project: Insights and Challenges","description":"In this video, I share insights from our car sales forecast project developed by machine learning team number three as part of the DSI program. We learned to use historical data to predict future trends, tackled challenges like data imbalance, and applied techniques such as class weighting during model training. I also highlighted the importance of balancing precision and recall, using the F1 score for our predictions. If I had more time, I would enhance our synthetic features with real data to improve our analysis. I encourage you to consider how we can further integrate real-world data and advanced models in future projects."}