<?xml version="1.0" encoding="UTF-8"?>
<rss xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:taxo="http://purl.org/rss/1.0/modules/taxonomy/" version="2.0">
  <channel>
    <title>topic Re: Help with ML finding RCA from dimensions in Knowledge Management</title>
    <link>https://community.splunk.com/t5/Knowledge-Management/Help-with-ML-finding-RCA-from-dimensions/m-p/469799#M8134</link>
    <description>&lt;P&gt;Predict Categorical Assistant could be applied on this straight ahead using MLTK or you can use classifier algorithms like Random Forest Classifier directly via spl.&lt;/P&gt;</description>
    <pubDate>Fri, 25 Oct 2019 16:05:40 GMT</pubDate>
    <dc:creator>hkeswani_splunk</dc:creator>
    <dc:date>2019-10-25T16:05:40Z</dc:date>
    <item>
      <title>Help with ML finding RCA from dimensions</title>
      <link>https://community.splunk.com/t5/Knowledge-Management/Help-with-ML-finding-RCA-from-dimensions/m-p/469798#M8133</link>
      <description>&lt;P&gt;Hello, first steps with ML, appreciate guidance on which ML method to use to get started.&lt;/P&gt;

&lt;P&gt;We have a set of metrics marked as Good\Bad and we want to identify a probable root cause based on the various dimensions.&lt;/P&gt;

&lt;UL&gt;
&lt;LI&gt;See below CSV example, there are 2 entries with bad values for metric "health"&lt;/LI&gt;
&lt;LI&gt;There are multiple dimensions OS, Server, Storage&lt;/LI&gt;
&lt;LI&gt;in this case the root cause is OS = Win7, which is easy to point out&lt;/LI&gt;
&lt;/UL&gt;

&lt;P&gt;What ML method can be used to provide the correct result?&lt;/P&gt;

&lt;P&gt;Thanks!&lt;/P&gt;

&lt;P&gt;Name,metric_name,result,OS,Server,Storage&lt;BR /&gt;
PC-1,health,good,Win10,Server1,S1&lt;BR /&gt;
PC-2,health,good,Win10,Server2,S1&lt;BR /&gt;
PC-3,health,good,Win10,Server3,S1&lt;BR /&gt;
PC-4,health,good,Win10,Server1,S1&lt;BR /&gt;
PC-5,health,good,Win10,Server2,S1&lt;BR /&gt;
PC-6,health,good,Win10,Server3,S2&lt;BR /&gt;
PC-7,health,good,Win10,Server1,S2&lt;BR /&gt;
PC-8,health,good,Win10,Server2,S2&lt;BR /&gt;
PC-9,health,bad,Win7,Server3,S2&lt;BR /&gt;
PC-10,health,bad,Win7,Server1,S2&lt;/P&gt;</description>
      <pubDate>Fri, 25 Oct 2019 10:58:38 GMT</pubDate>
      <guid>https://community.splunk.com/t5/Knowledge-Management/Help-with-ML-finding-RCA-from-dimensions/m-p/469798#M8133</guid>
      <dc:creator>kuzkuz</dc:creator>
      <dc:date>2019-10-25T10:58:38Z</dc:date>
    </item>
    <item>
      <title>Re: Help with ML finding RCA from dimensions</title>
      <link>https://community.splunk.com/t5/Knowledge-Management/Help-with-ML-finding-RCA-from-dimensions/m-p/469799#M8134</link>
      <description>&lt;P&gt;Predict Categorical Assistant could be applied on this straight ahead using MLTK or you can use classifier algorithms like Random Forest Classifier directly via spl.&lt;/P&gt;</description>
      <pubDate>Fri, 25 Oct 2019 16:05:40 GMT</pubDate>
      <guid>https://community.splunk.com/t5/Knowledge-Management/Help-with-ML-finding-RCA-from-dimensions/m-p/469799#M8134</guid>
      <dc:creator>hkeswani_splunk</dc:creator>
      <dc:date>2019-10-25T16:05:40Z</dc:date>
    </item>
  </channel>
</rss>

