<?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/bfb9829813a740229c51648a8de1b441&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/bfb9829813a740229c51648a8de1b441-87be377c011f46cf.gif</thumbnail_url><duration>134.356</duration><title>Operationalizing Fraud Models</title><description>In this video, I discuss the final steps of operationalizing a fraud model, focusing on how to effectively manage user reviews. I explain the importance of automatic banning for certain users while ensuring we still gather verified labels for accuracy. I also share the probability thresholds we use for alerts and how we simulate the process in our test database. Please take a moment to review the thresholds and provide any feedback.</description></oembed>