https://communities.sas.com/t5/SAS-Data-Science/A-problem-with-oversampling-and-SMOTE-in-SAS-Enterprise-Miner/m-p/738782#M8661 <P>Hi, I have a heavily imbalanced dataset with the rare target level at around 1% (binary variable)&nbsp;and I have 20000 observations in my training set (200 rare events). I need to get a sample with ~40000 observations where 50% of them are the rare event. I tried to use the sample node and do the standard oversampling in enterprise miner (see screenshot) as described here&nbsp;<A href="https://support.sas.com/kb/24/205.html)" target="_blank">https://support.sas.com/kb/24/205.html</A></P><P>But all I get is a sample of 400 with the original 200 rare events so it is basically doing undersampling rather than</P><P>oversampling...</P><P><span class="lia-inline-image-display-wrapper lia-image-align-inline" image-alt="SAS EM.png" style="width: 999px;"><img src="https://communities.sas.com/t5/image/serverpage/image-id/58997iFD5C06C8031DAEBC/image-size/large?v=v2&amp;px=999" role="button" title="SAS EM.png" alt="SAS EM.png" /></span></P><P>I would also like to use SMOTE rather than simple duplications but I do not see the option on Enterprise Miner. I checked all the other posts on SMOTE including all the links here&nbsp;<A href="https://communities.sas.com/t5/Statistical-Procedures/Assistance-with-SAS-code-for-SMOTE-and-adaptive-synthetic/m-p/257442" target="_blank">https://communities.sas.com/t5/Statistical-Procedures/Assistance-with-SAS-code-for-SMOTE-and-adaptive-synthetic/m-p/257442</A>&nbsp;but the sample SAS codes are difficult to understand and apply.</P><P>Can anybody help me with these two issues?</P><P>PS. My dataset contains both numeric and character input (predictor) variables.</P> Tue, 04 May 2021 04:38:17 GMT Alirezax 2021-05-04T04:38:17Z https://communities.sas.com/t5/SAS-Data-Science/A-problem-with-oversampling-and-SMOTE-in-SAS-Enterprise-Miner/m-p/738782#M8661 <P>Hi, I have a heavily imbalanced dataset with the rare target level at around 1% (binary variable)&nbsp;and I have 20000 observations in my training set (200 rare events). I need to get a sample with ~40000 observations where 50% of them are the rare event. I tried to use the sample node and do the standard oversampling in enterprise miner (see screenshot) as described here&nbsp;<A href="https://support.sas.com/kb/24/205.html)" target="_blank">https://support.sas.com/kb/24/205.html</A></P><P>But all I get is a sample of 400 with the original 200 rare events so it is basically doing undersampling rather than</P><P>oversampling...</P><P><span class="lia-inline-image-display-wrapper lia-image-align-inline" image-alt="SAS EM.png" style="width: 999px;"><img src="https://communities.sas.com/t5/image/serverpage/image-id/58997iFD5C06C8031DAEBC/image-size/large?v=v2&amp;px=999" role="button" title="SAS EM.png" alt="SAS EM.png" /></span></P><P>I would also like to use SMOTE rather than simple duplications but I do not see the option on Enterprise Miner. I checked all the other posts on SMOTE including all the links here&nbsp;<A href="https://communities.sas.com/t5/Statistical-Procedures/Assistance-with-SAS-code-for-SMOTE-and-adaptive-synthetic/m-p/257442" target="_blank">https://communities.sas.com/t5/Statistical-Procedures/Assistance-with-SAS-code-for-SMOTE-and-adaptive-synthetic/m-p/257442</A>&nbsp;but the sample SAS codes are difficult to understand and apply.</P><P>Can anybody help me with these two issues?</P><P>PS. My dataset contains both numeric and character input (predictor) variables.</P> Tue, 04 May 2021 04:38:17 GMT https://communities.sas.com/t5/SAS-Data-Science/A-problem-with-oversampling-and-SMOTE-in-SAS-Enterprise-Miner/m-p/738782#M8661 Alirezax 2021-05-04T04:38:17Z https://communities.sas.com/t5/SAS-Data-Science/A-problem-with-oversampling-and-SMOTE-in-SAS-Enterprise-Miner/m-p/739482#M8662 <P>Oversampling is a misnomer.&nbsp; It is actually undersampling as you've experienced.</P> Thu, 06 May 2021 13:48:36 GMT https://communities.sas.com/t5/SAS-Data-Science/A-problem-with-oversampling-and-SMOTE-in-SAS-Enterprise-Miner/m-p/739482#M8662 WendyCzika 2021-05-06T13:48:36Z