<?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/04b6ff11659142c7b20b5fb128cda4b4&quot; frameborder=&quot;0&quot; width=&quot;1232&quot; height=&quot;924&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>924</height><width>1232</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>924</thumbnail_height><thumbnail_width>1232</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/04b6ff11659142c7b20b5fb128cda4b4-b7f21172a6b9a08b.gif</thumbnail_url><duration>431.152</duration><title>Outfindo</title><description>In this video, I share some thoughts on how we can improve your recommendation system. I believe that starting from the user&apos;s problem rather than just product characteristics could lead to better results. I provide examples using TVs, bikes, and phones to illustrate how focusing on tasks can clarify the selection process. I also suggest that we could educate users about different categories in a more effective way. Please consider these suggestions and let me know your thoughts!</description></oembed>