{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/cdda1f4155d84e51b517708cc1e6f167\" 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/cdda1f4155d84e51b517708cc1e6f167-ecf2f8884552732e.gif","duration":309.59,"title":"Netflix Analytics and Popularity Prediction System on Databricks 📊","description":"In this video, I share my Databricks hackathon project focused on Netflix Analytics and Popularity Prediction, where I analyzed over 8,800 Netflix titles to uncover content patterns and built an ML model to predict show popularity. I imported the data from Kaggle, cleaned it, and ran SQL queries to identify key insights, such as 70% of the content being movies and a notable spike in content acquisition from 2019 to 2020. My classification model, which initially showed around 80% accuracy, was fine-tuned to achieve 86% accuracy using random forest algorithms. I also developed an interactive dashboard for stakeholders to explore the data visually. I encourage viewers to engage with the dashboard and utilize the insights for decision-making."}