Understanding the Gini/AUC metric as out-of-development performance metric












0












$begingroup$


Assume we develop a model for a binary classification task that reaches a certain Gini/AUROC estimate on the validation ( or training ) sample, among others. This is an overall good metric, often used for evaluating the ability of the model to separate the samples into, say, goods vs bads.



Further, assume this model is adequate and will be used for further collection of new samples with a certain cutoff value. What should be expected Gini/AUC estimates on the newly collected sample?



From what I'm noticing, on the training sample there were clear cases where the model was able to distinguish and separate it with large probabilities. On the other hand, with applied cuttoff, say, <50%, the new sample with collect only those cases where no such clear separation is possible (because if it would, the case might not get collected). With such approach, for me it seems logical that the overall separation in the new sample will be lower, resulting in lower out-of-development-period Gini/AUC.



Is this the expected behaviour in normal production environments? Am I understanding things correctly?



Note: I understand that there are other simple metrics, such as sensitivity/specificity, hoslem.test and others, allowing for measuring and visualising True/False Positives. However, I have found that Gini/AUC is often a key metric when discussing and comparing classification models.










share|improve this question











$endgroup$

















    0












    $begingroup$


    Assume we develop a model for a binary classification task that reaches a certain Gini/AUROC estimate on the validation ( or training ) sample, among others. This is an overall good metric, often used for evaluating the ability of the model to separate the samples into, say, goods vs bads.



    Further, assume this model is adequate and will be used for further collection of new samples with a certain cutoff value. What should be expected Gini/AUC estimates on the newly collected sample?



    From what I'm noticing, on the training sample there were clear cases where the model was able to distinguish and separate it with large probabilities. On the other hand, with applied cuttoff, say, <50%, the new sample with collect only those cases where no such clear separation is possible (because if it would, the case might not get collected). With such approach, for me it seems logical that the overall separation in the new sample will be lower, resulting in lower out-of-development-period Gini/AUC.



    Is this the expected behaviour in normal production environments? Am I understanding things correctly?



    Note: I understand that there are other simple metrics, such as sensitivity/specificity, hoslem.test and others, allowing for measuring and visualising True/False Positives. However, I have found that Gini/AUC is often a key metric when discussing and comparing classification models.










    share|improve this question











    $endgroup$















      0












      0








      0





      $begingroup$


      Assume we develop a model for a binary classification task that reaches a certain Gini/AUROC estimate on the validation ( or training ) sample, among others. This is an overall good metric, often used for evaluating the ability of the model to separate the samples into, say, goods vs bads.



      Further, assume this model is adequate and will be used for further collection of new samples with a certain cutoff value. What should be expected Gini/AUC estimates on the newly collected sample?



      From what I'm noticing, on the training sample there were clear cases where the model was able to distinguish and separate it with large probabilities. On the other hand, with applied cuttoff, say, <50%, the new sample with collect only those cases where no such clear separation is possible (because if it would, the case might not get collected). With such approach, for me it seems logical that the overall separation in the new sample will be lower, resulting in lower out-of-development-period Gini/AUC.



      Is this the expected behaviour in normal production environments? Am I understanding things correctly?



      Note: I understand that there are other simple metrics, such as sensitivity/specificity, hoslem.test and others, allowing for measuring and visualising True/False Positives. However, I have found that Gini/AUC is often a key metric when discussing and comparing classification models.










      share|improve this question











      $endgroup$




      Assume we develop a model for a binary classification task that reaches a certain Gini/AUROC estimate on the validation ( or training ) sample, among others. This is an overall good metric, often used for evaluating the ability of the model to separate the samples into, say, goods vs bads.



      Further, assume this model is adequate and will be used for further collection of new samples with a certain cutoff value. What should be expected Gini/AUC estimates on the newly collected sample?



      From what I'm noticing, on the training sample there were clear cases where the model was able to distinguish and separate it with large probabilities. On the other hand, with applied cuttoff, say, <50%, the new sample with collect only those cases where no such clear separation is possible (because if it would, the case might not get collected). With such approach, for me it seems logical that the overall separation in the new sample will be lower, resulting in lower out-of-development-period Gini/AUC.



      Is this the expected behaviour in normal production environments? Am I understanding things correctly?



      Note: I understand that there are other simple metrics, such as sensitivity/specificity, hoslem.test and others, allowing for measuring and visualising True/False Positives. However, I have found that Gini/AUC is often a key metric when discussing and comparing classification models.







      classification metric






      share|improve this question















      share|improve this question













      share|improve this question




      share|improve this question








      edited Dec 3 '18 at 10:01







      Nutle

















      asked Dec 3 '18 at 9:51









      NutleNutle

      18117




      18117






















          1 Answer
          1






          active

          oldest

          votes


















          0












          $begingroup$

          The advantage which train/test/validation dataset separation has is that you separate your dataset into:




          • The individuals which you know the exogenous variables and the output: Training

          • The individuals which you know the exogenous variables and the output (but you suppose you don't know which the output is): Test

          • The individuals you know the exogenous variables but not the output: Validation


          Every DS or ML model is made so it is prepared to receive a validation dataset in the future and try to get every metric just almost as good as if it was the train dataset.



          The test dataset has the objective of simulating the situation of having data but not output, and then you have the output to measure the behaviour and comparing the modelled vs real output.



          So, for a concrete answer:
          The behaviour you should expect from the validation (or newly collected sample) is the same as the test dataset.



          Given that the underlying phenomenon and sampling technique remains the same.



          For more information:
          https://towardsdatascience.com/train-validation-and-test-sets-72cb40cba9e7






          share|improve this answer








          New contributor




          Juan Esteban de la Calle is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
          Check out our Code of Conduct.






          $endgroup$













          • $begingroup$
            Thanks. My main question in a way is about AUC as a metric, which is a full sample based metric. Naturally, its properties should change when the validation sample is censored (applied cutoff rule), but how much change is expected? I understand there are other metrics, but gini/auc are too popular to ignore :)
            $endgroup$
            – Nutle
            yesterday










          • $begingroup$
            In other words, after applying cutoff, as in your bolded sentence, the sampling technique will not be the same anymore. So, whats then?
            $endgroup$
            – Nutle
            yesterday






          • 1




            $begingroup$
            There is no metric which is more or less sensitive to overfitting than others, so from AUC/Gini you should expect the same: You should expect the same decreased as when comparing test vs train datasets.
            $endgroup$
            – Juan Esteban de la Calle
            yesterday










          • $begingroup$
            If gini measures separability between (say) two classes, goods and bads, would you agree that after applying a certain cutoff, removing cases that are certainly bad, the gini of the new sample will surely be lower? Since if we remove the low hanging fruit, the remaining level of separability must decrease - because in other case, I would proceed to remove them until the separation is not clear/certain enough?
            $endgroup$
            – Nutle
            yesterday












          • $begingroup$
            Let me recap, you collect future samples based on the results of your previous model?
            $endgroup$
            – Juan Esteban de la Calle
            yesterday












          Your Answer








          StackExchange.ready(function() {
          var channelOptions = {
          tags: "".split(" "),
          id: "557"
          };
          initTagRenderer("".split(" "), "".split(" "), channelOptions);

          StackExchange.using("externalEditor", function() {
          // Have to fire editor after snippets, if snippets enabled
          if (StackExchange.settings.snippets.snippetsEnabled) {
          StackExchange.using("snippets", function() {
          createEditor();
          });
          }
          else {
          createEditor();
          }
          });

          function createEditor() {
          StackExchange.prepareEditor({
          heartbeatType: 'answer',
          autoActivateHeartbeat: false,
          convertImagesToLinks: false,
          noModals: true,
          showLowRepImageUploadWarning: true,
          reputationToPostImages: null,
          bindNavPrevention: true,
          postfix: "",
          imageUploader: {
          brandingHtml: "Powered by u003ca class="icon-imgur-white" href="https://imgur.com/"u003eu003c/au003e",
          contentPolicyHtml: "User contributions licensed under u003ca href="https://creativecommons.org/licenses/by-sa/3.0/"u003ecc by-sa 3.0 with attribution requiredu003c/au003e u003ca href="https://stackoverflow.com/legal/content-policy"u003e(content policy)u003c/au003e",
          allowUrls: true
          },
          onDemand: true,
          discardSelector: ".discard-answer"
          ,immediatelyShowMarkdownHelp:true
          });


          }
          });














          draft saved

          draft discarded


















          StackExchange.ready(
          function () {
          StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fdatascience.stackexchange.com%2fquestions%2f42029%2funderstanding-the-gini-auc-metric-as-out-of-development-performance-metric%23new-answer', 'question_page');
          }
          );

          Post as a guest















          Required, but never shown

























          1 Answer
          1






          active

          oldest

          votes








          1 Answer
          1






          active

          oldest

          votes









          active

          oldest

          votes






          active

          oldest

          votes









          0












          $begingroup$

          The advantage which train/test/validation dataset separation has is that you separate your dataset into:




          • The individuals which you know the exogenous variables and the output: Training

          • The individuals which you know the exogenous variables and the output (but you suppose you don't know which the output is): Test

          • The individuals you know the exogenous variables but not the output: Validation


          Every DS or ML model is made so it is prepared to receive a validation dataset in the future and try to get every metric just almost as good as if it was the train dataset.



          The test dataset has the objective of simulating the situation of having data but not output, and then you have the output to measure the behaviour and comparing the modelled vs real output.



          So, for a concrete answer:
          The behaviour you should expect from the validation (or newly collected sample) is the same as the test dataset.



          Given that the underlying phenomenon and sampling technique remains the same.



          For more information:
          https://towardsdatascience.com/train-validation-and-test-sets-72cb40cba9e7






          share|improve this answer








          New contributor




          Juan Esteban de la Calle is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
          Check out our Code of Conduct.






          $endgroup$













          • $begingroup$
            Thanks. My main question in a way is about AUC as a metric, which is a full sample based metric. Naturally, its properties should change when the validation sample is censored (applied cutoff rule), but how much change is expected? I understand there are other metrics, but gini/auc are too popular to ignore :)
            $endgroup$
            – Nutle
            yesterday










          • $begingroup$
            In other words, after applying cutoff, as in your bolded sentence, the sampling technique will not be the same anymore. So, whats then?
            $endgroup$
            – Nutle
            yesterday






          • 1




            $begingroup$
            There is no metric which is more or less sensitive to overfitting than others, so from AUC/Gini you should expect the same: You should expect the same decreased as when comparing test vs train datasets.
            $endgroup$
            – Juan Esteban de la Calle
            yesterday










          • $begingroup$
            If gini measures separability between (say) two classes, goods and bads, would you agree that after applying a certain cutoff, removing cases that are certainly bad, the gini of the new sample will surely be lower? Since if we remove the low hanging fruit, the remaining level of separability must decrease - because in other case, I would proceed to remove them until the separation is not clear/certain enough?
            $endgroup$
            – Nutle
            yesterday












          • $begingroup$
            Let me recap, you collect future samples based on the results of your previous model?
            $endgroup$
            – Juan Esteban de la Calle
            yesterday
















          0












          $begingroup$

          The advantage which train/test/validation dataset separation has is that you separate your dataset into:




          • The individuals which you know the exogenous variables and the output: Training

          • The individuals which you know the exogenous variables and the output (but you suppose you don't know which the output is): Test

          • The individuals you know the exogenous variables but not the output: Validation


          Every DS or ML model is made so it is prepared to receive a validation dataset in the future and try to get every metric just almost as good as if it was the train dataset.



          The test dataset has the objective of simulating the situation of having data but not output, and then you have the output to measure the behaviour and comparing the modelled vs real output.



          So, for a concrete answer:
          The behaviour you should expect from the validation (or newly collected sample) is the same as the test dataset.



          Given that the underlying phenomenon and sampling technique remains the same.



          For more information:
          https://towardsdatascience.com/train-validation-and-test-sets-72cb40cba9e7






          share|improve this answer








          New contributor




          Juan Esteban de la Calle is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
          Check out our Code of Conduct.






          $endgroup$













          • $begingroup$
            Thanks. My main question in a way is about AUC as a metric, which is a full sample based metric. Naturally, its properties should change when the validation sample is censored (applied cutoff rule), but how much change is expected? I understand there are other metrics, but gini/auc are too popular to ignore :)
            $endgroup$
            – Nutle
            yesterday










          • $begingroup$
            In other words, after applying cutoff, as in your bolded sentence, the sampling technique will not be the same anymore. So, whats then?
            $endgroup$
            – Nutle
            yesterday






          • 1




            $begingroup$
            There is no metric which is more or less sensitive to overfitting than others, so from AUC/Gini you should expect the same: You should expect the same decreased as when comparing test vs train datasets.
            $endgroup$
            – Juan Esteban de la Calle
            yesterday










          • $begingroup$
            If gini measures separability between (say) two classes, goods and bads, would you agree that after applying a certain cutoff, removing cases that are certainly bad, the gini of the new sample will surely be lower? Since if we remove the low hanging fruit, the remaining level of separability must decrease - because in other case, I would proceed to remove them until the separation is not clear/certain enough?
            $endgroup$
            – Nutle
            yesterday












          • $begingroup$
            Let me recap, you collect future samples based on the results of your previous model?
            $endgroup$
            – Juan Esteban de la Calle
            yesterday














          0












          0








          0





          $begingroup$

          The advantage which train/test/validation dataset separation has is that you separate your dataset into:




          • The individuals which you know the exogenous variables and the output: Training

          • The individuals which you know the exogenous variables and the output (but you suppose you don't know which the output is): Test

          • The individuals you know the exogenous variables but not the output: Validation


          Every DS or ML model is made so it is prepared to receive a validation dataset in the future and try to get every metric just almost as good as if it was the train dataset.



          The test dataset has the objective of simulating the situation of having data but not output, and then you have the output to measure the behaviour and comparing the modelled vs real output.



          So, for a concrete answer:
          The behaviour you should expect from the validation (or newly collected sample) is the same as the test dataset.



          Given that the underlying phenomenon and sampling technique remains the same.



          For more information:
          https://towardsdatascience.com/train-validation-and-test-sets-72cb40cba9e7






          share|improve this answer








          New contributor




          Juan Esteban de la Calle is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
          Check out our Code of Conduct.






          $endgroup$



          The advantage which train/test/validation dataset separation has is that you separate your dataset into:




          • The individuals which you know the exogenous variables and the output: Training

          • The individuals which you know the exogenous variables and the output (but you suppose you don't know which the output is): Test

          • The individuals you know the exogenous variables but not the output: Validation


          Every DS or ML model is made so it is prepared to receive a validation dataset in the future and try to get every metric just almost as good as if it was the train dataset.



          The test dataset has the objective of simulating the situation of having data but not output, and then you have the output to measure the behaviour and comparing the modelled vs real output.



          So, for a concrete answer:
          The behaviour you should expect from the validation (or newly collected sample) is the same as the test dataset.



          Given that the underlying phenomenon and sampling technique remains the same.



          For more information:
          https://towardsdatascience.com/train-validation-and-test-sets-72cb40cba9e7







          share|improve this answer








          New contributor




          Juan Esteban de la Calle is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
          Check out our Code of Conduct.









          share|improve this answer



          share|improve this answer






          New contributor




          Juan Esteban de la Calle is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
          Check out our Code of Conduct.









          answered yesterday









          Juan Esteban de la CalleJuan Esteban de la Calle

          687




          687




          New contributor




          Juan Esteban de la Calle is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
          Check out our Code of Conduct.





          New contributor





          Juan Esteban de la Calle is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
          Check out our Code of Conduct.






          Juan Esteban de la Calle is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
          Check out our Code of Conduct.












          • $begingroup$
            Thanks. My main question in a way is about AUC as a metric, which is a full sample based metric. Naturally, its properties should change when the validation sample is censored (applied cutoff rule), but how much change is expected? I understand there are other metrics, but gini/auc are too popular to ignore :)
            $endgroup$
            – Nutle
            yesterday










          • $begingroup$
            In other words, after applying cutoff, as in your bolded sentence, the sampling technique will not be the same anymore. So, whats then?
            $endgroup$
            – Nutle
            yesterday






          • 1




            $begingroup$
            There is no metric which is more or less sensitive to overfitting than others, so from AUC/Gini you should expect the same: You should expect the same decreased as when comparing test vs train datasets.
            $endgroup$
            – Juan Esteban de la Calle
            yesterday










          • $begingroup$
            If gini measures separability between (say) two classes, goods and bads, would you agree that after applying a certain cutoff, removing cases that are certainly bad, the gini of the new sample will surely be lower? Since if we remove the low hanging fruit, the remaining level of separability must decrease - because in other case, I would proceed to remove them until the separation is not clear/certain enough?
            $endgroup$
            – Nutle
            yesterday












          • $begingroup$
            Let me recap, you collect future samples based on the results of your previous model?
            $endgroup$
            – Juan Esteban de la Calle
            yesterday


















          • $begingroup$
            Thanks. My main question in a way is about AUC as a metric, which is a full sample based metric. Naturally, its properties should change when the validation sample is censored (applied cutoff rule), but how much change is expected? I understand there are other metrics, but gini/auc are too popular to ignore :)
            $endgroup$
            – Nutle
            yesterday










          • $begingroup$
            In other words, after applying cutoff, as in your bolded sentence, the sampling technique will not be the same anymore. So, whats then?
            $endgroup$
            – Nutle
            yesterday






          • 1




            $begingroup$
            There is no metric which is more or less sensitive to overfitting than others, so from AUC/Gini you should expect the same: You should expect the same decreased as when comparing test vs train datasets.
            $endgroup$
            – Juan Esteban de la Calle
            yesterday










          • $begingroup$
            If gini measures separability between (say) two classes, goods and bads, would you agree that after applying a certain cutoff, removing cases that are certainly bad, the gini of the new sample will surely be lower? Since if we remove the low hanging fruit, the remaining level of separability must decrease - because in other case, I would proceed to remove them until the separation is not clear/certain enough?
            $endgroup$
            – Nutle
            yesterday












          • $begingroup$
            Let me recap, you collect future samples based on the results of your previous model?
            $endgroup$
            – Juan Esteban de la Calle
            yesterday
















          $begingroup$
          Thanks. My main question in a way is about AUC as a metric, which is a full sample based metric. Naturally, its properties should change when the validation sample is censored (applied cutoff rule), but how much change is expected? I understand there are other metrics, but gini/auc are too popular to ignore :)
          $endgroup$
          – Nutle
          yesterday




          $begingroup$
          Thanks. My main question in a way is about AUC as a metric, which is a full sample based metric. Naturally, its properties should change when the validation sample is censored (applied cutoff rule), but how much change is expected? I understand there are other metrics, but gini/auc are too popular to ignore :)
          $endgroup$
          – Nutle
          yesterday












          $begingroup$
          In other words, after applying cutoff, as in your bolded sentence, the sampling technique will not be the same anymore. So, whats then?
          $endgroup$
          – Nutle
          yesterday




          $begingroup$
          In other words, after applying cutoff, as in your bolded sentence, the sampling technique will not be the same anymore. So, whats then?
          $endgroup$
          – Nutle
          yesterday




          1




          1




          $begingroup$
          There is no metric which is more or less sensitive to overfitting than others, so from AUC/Gini you should expect the same: You should expect the same decreased as when comparing test vs train datasets.
          $endgroup$
          – Juan Esteban de la Calle
          yesterday




          $begingroup$
          There is no metric which is more or less sensitive to overfitting than others, so from AUC/Gini you should expect the same: You should expect the same decreased as when comparing test vs train datasets.
          $endgroup$
          – Juan Esteban de la Calle
          yesterday












          $begingroup$
          If gini measures separability between (say) two classes, goods and bads, would you agree that after applying a certain cutoff, removing cases that are certainly bad, the gini of the new sample will surely be lower? Since if we remove the low hanging fruit, the remaining level of separability must decrease - because in other case, I would proceed to remove them until the separation is not clear/certain enough?
          $endgroup$
          – Nutle
          yesterday






          $begingroup$
          If gini measures separability between (say) two classes, goods and bads, would you agree that after applying a certain cutoff, removing cases that are certainly bad, the gini of the new sample will surely be lower? Since if we remove the low hanging fruit, the remaining level of separability must decrease - because in other case, I would proceed to remove them until the separation is not clear/certain enough?
          $endgroup$
          – Nutle
          yesterday














          $begingroup$
          Let me recap, you collect future samples based on the results of your previous model?
          $endgroup$
          – Juan Esteban de la Calle
          yesterday




          $begingroup$
          Let me recap, you collect future samples based on the results of your previous model?
          $endgroup$
          – Juan Esteban de la Calle
          yesterday


















          draft saved

          draft discarded




















































          Thanks for contributing an answer to Data Science Stack Exchange!


          • Please be sure to answer the question. Provide details and share your research!

          But avoid



          • Asking for help, clarification, or responding to other answers.

          • Making statements based on opinion; back them up with references or personal experience.


          Use MathJax to format equations. MathJax reference.


          To learn more, see our tips on writing great answers.




          draft saved


          draft discarded














          StackExchange.ready(
          function () {
          StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fdatascience.stackexchange.com%2fquestions%2f42029%2funderstanding-the-gini-auc-metric-as-out-of-development-performance-metric%23new-answer', 'question_page');
          }
          );

          Post as a guest















          Required, but never shown





















































          Required, but never shown














          Required, but never shown












          Required, but never shown







          Required, but never shown

































          Required, but never shown














          Required, but never shown












          Required, but never shown







          Required, but never shown







          Popular posts from this blog

          How to label and detect the document text images

          Vallis Paradisi

          Tabula Rosettana