<?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: How to use splunk MLTK to detect outliers in case to find latency anomalies? in Splunk Search</title>
    <link>https://community.splunk.com/t5/Splunk-Search/How-to-use-splunk-MLTK-to-detect-outliers-in-case-to-find/m-p/646185#M223685</link>
    <description>&lt;P&gt;can i do something like this&lt;BR /&gt;&lt;BR /&gt;sourcetype="something"&lt;BR /&gt;| fields duration, operation&lt;BR /&gt;| bin _time span=5m&lt;BR /&gt;| stats avg(duration) as avg_duration by operation, _time&lt;BR /&gt;| streamstats window=0 avg(avg_duration) as mean_duration stdev(avg_duration) as stdev_duration by identity_operation&lt;BR /&gt;| eval normalized_duration = (avg_duration - mean_duration) / stdev_duration&lt;BR /&gt;| eventstats avg(normalized_duration) as avg_normalized_duration by operation&lt;BR /&gt;| eval normalized_duration = (normalized_duration - avg_normalized_duration) / stdev(avg_normalized_duration)&lt;BR /&gt;| fit IsolationForestModel normalized_duration by operation&lt;BR /&gt;| eval anomaly = if(predicted_IsolationForestModel = 1, 0, 1)&lt;BR /&gt;| table identity_operation, _time, avg_duration, anomaly&lt;BR /&gt;&lt;BR /&gt;as stdev is not supported in splunk what can i use instead?&lt;/P&gt;</description>
    <pubDate>Wed, 07 Jun 2023 17:56:11 GMT</pubDate>
    <dc:creator>amitrinx</dc:creator>
    <dc:date>2023-06-07T17:56:11Z</dc:date>
    <item>
      <title>How to use splunk MLTK to detect outliers in case to find latency anomalies?</title>
      <link>https://community.splunk.com/t5/Splunk-Search/How-to-use-splunk-MLTK-to-detect-outliers-in-case-to-find/m-p/646080#M223662</link>
      <description>&lt;P&gt;Hi Team,&amp;nbsp;&lt;BR /&gt;I have a field "duration". There are lot of APIs for which this field is populated&lt;BR /&gt;can i use the Detect outliers to find out out high duration instances in the last 7 days based on API name.&lt;BR /&gt;&lt;BR /&gt;As i am new to this. i don't know how to start. can someone help?&lt;/P&gt;</description>
      <pubDate>Wed, 07 Jun 2023 10:54:04 GMT</pubDate>
      <guid>https://community.splunk.com/t5/Splunk-Search/How-to-use-splunk-MLTK-to-detect-outliers-in-case-to-find/m-p/646080#M223662</guid>
      <dc:creator>amitrinx</dc:creator>
      <dc:date>2023-06-07T10:54:04Z</dc:date>
    </item>
    <item>
      <title>Re: How to use splunk MLTK to detect outliers in case to find latency anomalies</title>
      <link>https://community.splunk.com/t5/Splunk-Search/How-to-use-splunk-MLTK-to-detect-outliers-in-case-to-find/m-p/646087#M223665</link>
      <description>&lt;P&gt;MLTK detects anomalies by looking at deviations from a model of "expected" behaviour, so the first thing you need to do is create a search which returns what you decide is normal behaviour. In your case, this could be average duration per API per hour/day/whatever time period is appropriate for your data. The tricky bit is that you may need to create a model for each API (which isn't ideal). A workaround to this is to normalise the data in some way.&lt;/P&gt;</description>
      <pubDate>Wed, 07 Jun 2023 10:58:40 GMT</pubDate>
      <guid>https://community.splunk.com/t5/Splunk-Search/How-to-use-splunk-MLTK-to-detect-outliers-in-case-to-find/m-p/646087#M223665</guid>
      <dc:creator>ITWhisperer</dc:creator>
      <dc:date>2023-06-07T10:58:40Z</dc:date>
    </item>
    <item>
      <title>Re: How to use splunk MLTK to detect outliers in case to find latency anomalies?</title>
      <link>https://community.splunk.com/t5/Splunk-Search/How-to-use-splunk-MLTK-to-detect-outliers-in-case-to-find/m-p/646185#M223685</link>
      <description>&lt;P&gt;can i do something like this&lt;BR /&gt;&lt;BR /&gt;sourcetype="something"&lt;BR /&gt;| fields duration, operation&lt;BR /&gt;| bin _time span=5m&lt;BR /&gt;| stats avg(duration) as avg_duration by operation, _time&lt;BR /&gt;| streamstats window=0 avg(avg_duration) as mean_duration stdev(avg_duration) as stdev_duration by identity_operation&lt;BR /&gt;| eval normalized_duration = (avg_duration - mean_duration) / stdev_duration&lt;BR /&gt;| eventstats avg(normalized_duration) as avg_normalized_duration by operation&lt;BR /&gt;| eval normalized_duration = (normalized_duration - avg_normalized_duration) / stdev(avg_normalized_duration)&lt;BR /&gt;| fit IsolationForestModel normalized_duration by operation&lt;BR /&gt;| eval anomaly = if(predicted_IsolationForestModel = 1, 0, 1)&lt;BR /&gt;| table identity_operation, _time, avg_duration, anomaly&lt;BR /&gt;&lt;BR /&gt;as stdev is not supported in splunk what can i use instead?&lt;/P&gt;</description>
      <pubDate>Wed, 07 Jun 2023 17:56:11 GMT</pubDate>
      <guid>https://community.splunk.com/t5/Splunk-Search/How-to-use-splunk-MLTK-to-detect-outliers-in-case-to-find/m-p/646185#M223685</guid>
      <dc:creator>amitrinx</dc:creator>
      <dc:date>2023-06-07T17:56:11Z</dc:date>
    </item>
    <item>
      <title>Re: How to use splunk MLTK to detect outliers in case to find latency anomalies?</title>
      <link>https://community.splunk.com/t5/Splunk-Search/How-to-use-splunk-MLTK-to-detect-outliers-in-case-to-find/m-p/646211#M223687</link>
      <description>&lt;P&gt;stdev is supported as an aggregation function to stats commands not a function to eval command&lt;/P&gt;</description>
      <pubDate>Wed, 07 Jun 2023 20:38:02 GMT</pubDate>
      <guid>https://community.splunk.com/t5/Splunk-Search/How-to-use-splunk-MLTK-to-detect-outliers-in-case-to-find/m-p/646211#M223687</guid>
      <dc:creator>ITWhisperer</dc:creator>
      <dc:date>2023-06-07T20:38:02Z</dc:date>
    </item>
  </channel>
</rss>

