<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Opentv on Gidley&#39;s Gossipings</title>
    <link>https://gidley.co.uk/tags/opentv/</link>
    <description>Recent content in Opentv on Gidley&#39;s Gossipings</description>
    <generator>Hugo</generator>
    <language>en</language>
    <lastBuildDate>Wed, 09 Sep 2026 00:00:00 +0100</lastBuildDate>
    <atom:link href="https://gidley.co.uk/tags/opentv/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>OpenTV: Actionable Rails Analytics</title>
      <link>https://gidley.co.uk/post/opentv-invents-actionable-rails-analytics/</link>
      <pubDate>Wed, 09 Sep 2026 00:00:00 +0100</pubDate>
      <guid>https://gidley.co.uk/post/opentv-invents-actionable-rails-analytics/</guid>
      <description>&lt;p&gt;Most analytics on a TV interface end up in the same place: a dashboard someone checks once a quarter. This is useful for a retrospective, useless in the moment when a rail is actively showing the wrong things to the wrong person.&lt;/p&gt;&#xA;&lt;p&gt;Actionable Rails Analytics, is built on a simpler premise — measurement should feed straight back to the person and systems managing the rail it&amp;rsquo;s measuring, not into a report about the rail. Engagement signals on individual tiles get tracked live, and that signal directly is available to the editor curating the rails.&lt;/p&gt;</description>
    </item>
    <item>
      <title>OpenTV: Personalized Reviews</title>
      <link>https://gidley.co.uk/post/opentv-invents-personalized-reviews/</link>
      <pubDate>Mon, 07 Sep 2026 11:00:00 +0100</pubDate>
      <guid>https://gidley.co.uk/post/opentv-invents-personalized-reviews/</guid>
      <description>&lt;p&gt;Plenty of people have a negative reaction to recommendations. The suggestions might be perfectly good, but they don&amp;rsquo;t much like the idea that a machine knows them. We hear that in customer feedback, and we can see it in the data — a rail explicitly labelled as recommendations gets less engagement than exactly the same weighting applied quietly inside an ordinary list or a set of search results.&lt;/p&gt;&#xA;&lt;p&gt;So instead of hiding the AI harder, we went the other way. Personalized Reviews (patent pending) puts the model that does the recommending into the audience&amp;rsquo;s hands, in a form that reads as human rather than statistical.&lt;/p&gt;</description>
    </item>
  </channel>
</rss>
