<?xml version="1.0" encoding="UTF-8"?><oembed><type>video</type><version>1.0</version><html>&lt;iframe src=&quot;https://www.loom.com/embed/71a4a1c7f0f347f796a7b89f716208a2&quot; frameborder=&quot;0&quot; width=&quot;1920&quot; height=&quot;1440&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>1440</height><width>1920</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>1440</thumbnail_height><thumbnail_width>1920</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/71a4a1c7f0f347f796a7b89f716208a2-cd245883bacc5070.gif</thumbnail_url><duration>340.975</duration><title>Bitcoin Prediction Engine Demo Updates and Issues 🔧</title><description>Hi, I am Aditya Koul, and this Loom is my update on the Bitcoin price prediction engine assessment. I followed the given requirements and set up the Docker Compose, then used XGBoost and a regularization focused XGBoost variant, Ray XGBoost, to reduce overfitting. The UI now shows live market status every 10 seconds with predictions, charts, export to Excel, and history views for 1 day to 1 year. I ran into issues with model updating and retraining, so values are not refreshing consistently yet. No action was specifically requested from you.</description></oembed>