<?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: Gain, Gain Chart and Cumulative Gain in SAS Academy for Data Science</title>
    <link>https://communities.sas.com/t5/SAS-Academy-for-Data-Science/Gain-Gain-Chart-and-Cumulative-Gain/m-p/646418#M747</link>
    <description>&lt;P&gt;&lt;STRONG&gt;1. Gain:&lt;/STRONG&gt;&lt;SPAN&gt;&amp;nbsp;this metric is reported in the Output window (under "Statistics Table") of the "Model Comparison" node (see page 6-7 of course notes); what is its formula/definition?&lt;/SPAN&gt;&lt;BR /&gt;&lt;SPAN&gt;Is this based on the definition given at page 256 of "Enterprise Miner 15.1: Reference Help": ((% of events in decile / random % of events in decile)-1).&lt;/SPAN&gt;&lt;BR /&gt;&lt;SPAN&gt;If so, what is its interpretation?&lt;/SPAN&gt;&lt;/P&gt;
&lt;P&gt;&lt;FONT face="arial black,avant garde" color="#0000FF"&gt;&lt;SPAN&gt;MY ANSWER:&lt;/SPAN&gt;&lt;/FONT&gt;&lt;/P&gt;
&lt;P&gt;&lt;FONT face="arial black,avant garde" color="#0000FF"&gt;&lt;SPAN&gt;Both LIFT and GAIN statistics are computed at the depth of 10th decile (by default) and Gain=Lift-1. The formula given above is correct for the Gain.&lt;/SPAN&gt;&lt;/FONT&gt;&lt;/P&gt;
&lt;P&gt;&lt;STRONG&gt;2. Gain Chart:&lt;/STRONG&gt;&lt;SPAN&gt;&amp;nbsp;this is the chart displayed as part of the "Score Ranking Overlay" output when selecting option "Gain"; below is a screenshot taken from the example/demonstration in "Lesson 7: Model Assessment Using SAS Enterprise Miner" (see also page 6-19 of the course notes); again, how are the values on the Y-axis calculated?&lt;/SPAN&gt;&lt;/P&gt;
&lt;P&gt;&lt;STRONG&gt;&lt;FONT color="#0000FF"&gt;My answer:&lt;/FONT&gt;&lt;/STRONG&gt;&lt;/P&gt;
&lt;P&gt;&lt;STRONG&gt;&lt;FONT color="#0000FF"&gt;The values Y-axis is Lift-1&lt;/FONT&gt;&lt;/STRONG&gt;&lt;/P&gt;
&lt;P&gt;&lt;SPAN&gt;&lt;STRONG&gt;3. Cumulative Gain:&lt;/STRONG&gt;&amp;nbsp;page 6-17 of the course notes states that "cumulative percent response" chart is more widely known as "cumulative gain" in the predictive modeling literature. It also adds that "[...] Plotting cumulative gain for all selection fractions yields a gains chart"; at page 6-20, it says "It is instructive to view the actual proportion of cases with the primary outcome (called gain or cumulative percent response) at each decile":&lt;BR /&gt;(a) from other sources on internet (see&amp;nbsp;&lt;A href="http://www2.cs.uregina.ca/~dbd/cs831/notes/lift_chart/lift_chart.html" target="_blank" rel="noopener nofollow noopener noreferrer"&gt;this&lt;/A&gt;&amp;nbsp;as an example), it seems that "cumulative gain" is related to the "percentage of the total possible positive responses (i.e. primary outcome events) at a given depth" (&lt;FONT&gt;in the "Score Ranking Overlay" window, that is given by "Cumulative % Capture Response"&lt;/FONT&gt;); is this just an example of inconsistency in the use of the same term?&lt;BR /&gt;(b) how does the "cumulative gain" differ from the Gain Chart in point (2) above?&lt;/SPAN&gt;&lt;/P&gt;
&lt;P&gt;&lt;FONT color="#0000FF"&gt;&lt;STRONG&gt;My answer:&lt;/STRONG&gt;&lt;/FONT&gt;&lt;/P&gt;
&lt;P&gt;&lt;FONT color="#0000FF"&gt;&lt;STRONG&gt;Cumulative gain is equal to&amp;nbsp;Cumulative %&amp;nbsp; Response, Therefore SAS EM is only showing&amp;nbsp;Cumulative %&amp;nbsp; Response. &lt;/STRONG&gt;&lt;/FONT&gt;&lt;/P&gt;
&lt;P&gt;&lt;FONT color="#0000FF"&gt;&lt;STRONG&gt;Please note that&amp;nbsp;Cumulative % Capture Response =&amp;nbsp;(Cumulative % of events in a decile / total number of events) is different from&amp;nbsp;Cumulative %&amp;nbsp; Response = (Cumulative % of events in a decile).&lt;/STRONG&gt;&lt;/FONT&gt;&lt;/P&gt;
&lt;P&gt;&lt;SPAN&gt;Please let me know if you have any further questions.&lt;/SPAN&gt;&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;</description>
    <pubDate>Sat, 09 May 2020 20:08:43 GMT</pubDate>
    <dc:creator>gcjfernandez</dc:creator>
    <dc:date>2020-05-09T20:08:43Z</dc:date>
    <item>
      <title>Gain, Gain Chart and Cumulative Gain</title>
      <link>https://communities.sas.com/t5/SAS-Academy-for-Data-Science/Gain-Gain-Chart-and-Cumulative-Gain/m-p/646208#M739</link>
      <description>&lt;DIV&gt;&lt;FONT style="background-color: #ffffff;"&gt;Re: &lt;FONT style="background-color: #ffffff; box-sizing: border-box; color: #333333; font-family: Arial,Helvetica,sans-serif; font-size: 16px; font-style: normal; font-variant: normal; font-weight: 300; letter-spacing: normal; orphans: 2; text-align: left; text-decoration: none; text-indent: 0px; text-transform: none; -webkit-text-stroke-width: 0px; white-space: normal; word-spacing: 0px;"&gt;Applied Analytics Using SAS Enterprise Miner&lt;/FONT&gt;&lt;/FONT&gt;&lt;/DIV&gt;
&lt;DIV&gt;&lt;FONT style="background-color: #ffffff;"&gt;I would be very grateful if someone could clarify the concepts/definitions of Gain, Gain Chart and Cumulative Gain, since I am a bit confused, probably due to the fact the terminology does not seem to be used consistently across the industry:&lt;/FONT&gt;&lt;/DIV&gt;
&lt;DIV&gt;&amp;nbsp;&lt;/DIV&gt;
&lt;DIV&gt;&lt;FONT style="background-color: #ffffff;"&gt;&lt;STRONG&gt;1. Gain:&lt;/STRONG&gt; this metric is reported in the Output window (under "Statistics Table") of the "Model Comparison" node (see page 6-7 of course notes); what is its formula/definition?&lt;BR /&gt;Is this based on the definition given at page 256 of "Enterprise Miner 15.1: Reference Help": ((% of events in decile / random % of events in decile)-1).&lt;BR /&gt;If so, what is its interpretation? &lt;/FONT&gt;&lt;/DIV&gt;
&lt;DIV&gt;&amp;nbsp;&lt;/DIV&gt;
&lt;DIV&gt;&lt;FONT style="background-color: #ffffff;"&gt;&lt;STRONG&gt;2. Gain Chart:&lt;/STRONG&gt; this is the chart displayed as part of the "Score Ranking Overlay" output when selecting option "Gain"; below is a screenshot taken from the example/demonstration in "Lesson 7: Model Assessment Using SAS Enterprise Miner" (see also page 6-19 of the course notes); again, how are the values on the Y-axis calculated?&lt;/FONT&gt;&lt;/DIV&gt;
&lt;DIV&gt;&lt;FONT style="background-color: #ffffff;"&gt;&lt;span class="lia-inline-image-display-wrapper lia-image-align-inline" image-alt="Gain_chart.png" style="width: 999px;"&gt;&lt;img src="https://communities.sas.com/t5/image/serverpage/image-id/39221iDAE6791B4CC620CE/image-size/large?v=v2&amp;amp;px=999" role="button" title="Gain_chart.png" alt="Gain_chart.png" /&gt;&lt;/span&gt;&lt;/FONT&gt;&lt;/DIV&gt;
&lt;DIV&gt;&amp;nbsp;&lt;/DIV&gt;
&lt;DIV&gt;&lt;FONT style="background-color: #ffffff;"&gt;&lt;STRONG&gt;3. Cumulative Gain:&lt;/STRONG&gt; page 6-17 of the course notes states that "cumulative percent response" chart is more widely known as "cumulative gain" in the predictive modeling literature. It also adds that "[...] Plotting cumulative gain for all selection fractions yields a gains chart"; at page 6-20, it says "It is instructive to view the actual proportion of cases with the primary outcome (called gain or cumulative percent response) at each decile":&lt;BR /&gt;(a) from other sources on internet (see &lt;A href="http://www2.cs.uregina.ca/~dbd/cs831/notes/lift_chart/lift_chart.html" target="_blank" rel="noopener"&gt;this&lt;/A&gt; as an example), it seems that "cumulative gain" is related to the "percentage of the total possible positive responses (i.e. primary outcome events) at a given depth" (&lt;FONT style="background-color: #ffffff; box-sizing: border-box; color: #333333; font-family: Arial,Helvetica,sans-serif; font-size: 16px; font-style: normal; font-variant: normal; font-weight: 300; letter-spacing: normal; orphans: 2; text-align: left; text-decoration: none; text-indent: 0px; text-transform: none; -webkit-text-stroke-width: 0px; white-space: normal; word-spacing: 0px;"&gt;in the "Score Ranking Overlay" window, that is given by "Cumulative % Capture Response"&lt;/FONT&gt;); is this just an example of inconsistency in the use of the same term?&lt;BR /&gt;(b) how does the "cumulative gain" differ from the Gain Chart in point (2) above?&lt;/FONT&gt;&lt;/DIV&gt;
&lt;DIV&gt;&amp;nbsp;&lt;/DIV&gt;</description>
      <pubDate>Fri, 08 May 2020 13:40:45 GMT</pubDate>
      <guid>https://communities.sas.com/t5/SAS-Academy-for-Data-Science/Gain-Gain-Chart-and-Cumulative-Gain/m-p/646208#M739</guid>
      <dc:creator>pvareschi</dc:creator>
      <dc:date>2020-05-08T13:40:45Z</dc:date>
    </item>
    <item>
      <title>Re: Gain, Gain Chart and Cumulative Gain</title>
      <link>https://communities.sas.com/t5/SAS-Academy-for-Data-Science/Gain-Gain-Chart-and-Cumulative-Gain/m-p/646418#M747</link>
      <description>&lt;P&gt;&lt;STRONG&gt;1. Gain:&lt;/STRONG&gt;&lt;SPAN&gt;&amp;nbsp;this metric is reported in the Output window (under "Statistics Table") of the "Model Comparison" node (see page 6-7 of course notes); what is its formula/definition?&lt;/SPAN&gt;&lt;BR /&gt;&lt;SPAN&gt;Is this based on the definition given at page 256 of "Enterprise Miner 15.1: Reference Help": ((% of events in decile / random % of events in decile)-1).&lt;/SPAN&gt;&lt;BR /&gt;&lt;SPAN&gt;If so, what is its interpretation?&lt;/SPAN&gt;&lt;/P&gt;
&lt;P&gt;&lt;FONT face="arial black,avant garde" color="#0000FF"&gt;&lt;SPAN&gt;MY ANSWER:&lt;/SPAN&gt;&lt;/FONT&gt;&lt;/P&gt;
&lt;P&gt;&lt;FONT face="arial black,avant garde" color="#0000FF"&gt;&lt;SPAN&gt;Both LIFT and GAIN statistics are computed at the depth of 10th decile (by default) and Gain=Lift-1. The formula given above is correct for the Gain.&lt;/SPAN&gt;&lt;/FONT&gt;&lt;/P&gt;
&lt;P&gt;&lt;STRONG&gt;2. Gain Chart:&lt;/STRONG&gt;&lt;SPAN&gt;&amp;nbsp;this is the chart displayed as part of the "Score Ranking Overlay" output when selecting option "Gain"; below is a screenshot taken from the example/demonstration in "Lesson 7: Model Assessment Using SAS Enterprise Miner" (see also page 6-19 of the course notes); again, how are the values on the Y-axis calculated?&lt;/SPAN&gt;&lt;/P&gt;
&lt;P&gt;&lt;STRONG&gt;&lt;FONT color="#0000FF"&gt;My answer:&lt;/FONT&gt;&lt;/STRONG&gt;&lt;/P&gt;
&lt;P&gt;&lt;STRONG&gt;&lt;FONT color="#0000FF"&gt;The values Y-axis is Lift-1&lt;/FONT&gt;&lt;/STRONG&gt;&lt;/P&gt;
&lt;P&gt;&lt;SPAN&gt;&lt;STRONG&gt;3. Cumulative Gain:&lt;/STRONG&gt;&amp;nbsp;page 6-17 of the course notes states that "cumulative percent response" chart is more widely known as "cumulative gain" in the predictive modeling literature. It also adds that "[...] Plotting cumulative gain for all selection fractions yields a gains chart"; at page 6-20, it says "It is instructive to view the actual proportion of cases with the primary outcome (called gain or cumulative percent response) at each decile":&lt;BR /&gt;(a) from other sources on internet (see&amp;nbsp;&lt;A href="http://www2.cs.uregina.ca/~dbd/cs831/notes/lift_chart/lift_chart.html" target="_blank" rel="noopener nofollow noopener noreferrer"&gt;this&lt;/A&gt;&amp;nbsp;as an example), it seems that "cumulative gain" is related to the "percentage of the total possible positive responses (i.e. primary outcome events) at a given depth" (&lt;FONT&gt;in the "Score Ranking Overlay" window, that is given by "Cumulative % Capture Response"&lt;/FONT&gt;); is this just an example of inconsistency in the use of the same term?&lt;BR /&gt;(b) how does the "cumulative gain" differ from the Gain Chart in point (2) above?&lt;/SPAN&gt;&lt;/P&gt;
&lt;P&gt;&lt;FONT color="#0000FF"&gt;&lt;STRONG&gt;My answer:&lt;/STRONG&gt;&lt;/FONT&gt;&lt;/P&gt;
&lt;P&gt;&lt;FONT color="#0000FF"&gt;&lt;STRONG&gt;Cumulative gain is equal to&amp;nbsp;Cumulative %&amp;nbsp; Response, Therefore SAS EM is only showing&amp;nbsp;Cumulative %&amp;nbsp; Response. &lt;/STRONG&gt;&lt;/FONT&gt;&lt;/P&gt;
&lt;P&gt;&lt;FONT color="#0000FF"&gt;&lt;STRONG&gt;Please note that&amp;nbsp;Cumulative % Capture Response =&amp;nbsp;(Cumulative % of events in a decile / total number of events) is different from&amp;nbsp;Cumulative %&amp;nbsp; Response = (Cumulative % of events in a decile).&lt;/STRONG&gt;&lt;/FONT&gt;&lt;/P&gt;
&lt;P&gt;&lt;SPAN&gt;Please let me know if you have any further questions.&lt;/SPAN&gt;&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;</description>
      <pubDate>Sat, 09 May 2020 20:08:43 GMT</pubDate>
      <guid>https://communities.sas.com/t5/SAS-Academy-for-Data-Science/Gain-Gain-Chart-and-Cumulative-Gain/m-p/646418#M747</guid>
      <dc:creator>gcjfernandez</dc:creator>
      <dc:date>2020-05-09T20:08:43Z</dc:date>
    </item>
  </channel>
</rss>

