<?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/6c1a8bb072b6423098c6ebd5c28e6dec&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/6c1a8bb072b6423098c6ebd5c28e6dec-dd7d0581c4c4c351.gif</thumbnail_url><duration>300.835</duration><title>Building a Custom Machine Learning Solution for Sensitive Information Detection</title><description>Hey everyone, GP here! In this video, I&apos;m sharing my work as a privacy engineer focused on building a system to detect sensitive information in documents, like credit card names. I discuss the lack of features for creating custom machine learning entities, specifically neuro entities for named entity recognition. I also demonstrate a tool for adding training examples and generating synthetic data to improve our model. I would love to get your feedback on this approach, especially if you have ideas on how to make it more business-oriented.</description></oembed>