tag:blogger.com,1999:blog-3721871707048712457.post6282184730139379357..comments2024-03-28T00:39:48.395-04:00Comments on Breaking BI: Azure Machine Learning: Model Evaluation and Threshold ManipulationBreaking BIhttp://www.blogger.com/profile/02551920506874509998noreply@blogger.comBlogger4125tag:blogger.com,1999:blog-3721871707048712457.post-54513305644159840042017-10-18T15:52:10.134-04:002017-10-18T15:52:10.134-04:00If you evaluate a model's performance and dete...If you evaluate a model's performance and determine that it works best at a threshold that is different from the default of .5, how can you train the model with the different threshold to achieve more optimal results?Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-3721871707048712457.post-75106064054497146342017-08-29T09:29:44.009-04:002017-08-29T09:29:44.009-04:00The output from "Score Model" contains a...The output from "Score Model" contains a "Scored Probabilities" column. We could easily use a custom SQL/R/Python script to add a new field to our dataset using an IF or CASE statement. However, this new field may not work with "Evaluate Model" anymore. Alas, you could always use the slicer in "Evaluate Model" to tinker with the thresholds in the viz.<br />Breaking BIhttps://www.blogger.com/profile/02551920506874509998noreply@blogger.comtag:blogger.com,1999:blog-3721871707048712457.post-21636730665776703582017-08-29T08:51:42.398-04:002017-08-29T08:51:42.398-04:00Once we know our ideal threshold, how do we tell A...Once we know our ideal threshold, how do we tell Azure to use this threshold for classification?<br />Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-3721871707048712457.post-1171234867202645112017-06-13T12:32:37.923-04:002017-06-13T12:32:37.923-04:00awesome break down of that confusing "Evaluat...awesome break down of that confusing "Evaluation Table" . Thanks so much!Anonymoushttps://www.blogger.com/profile/12765628965085528229noreply@blogger.com