{"id":134,"date":"2021-07-16T16:10:27","date_gmt":"2021-07-16T16:10:27","guid":{"rendered":"https:\/\/felixaugenstein.com\/blog\/?p=134"},"modified":"2021-07-16T16:10:27","modified_gmt":"2021-07-16T16:10:27","slug":"monitor-your-deployed-machine-learning-models-with-watson-openscale","status":"publish","type":"post","link":"https:\/\/felixaugenstein.com\/blog\/monitor-your-deployed-machine-learning-models-with-watson-openscale\/","title":{"rendered":"Monitor your deployed machine learning models with Watson OpenScale"},"content":{"rendered":"\n

In this hands-on tutorial you will learn how Watson OpenScale can be used to monitor your deployed machine learning models<\/p>\n\n\n\n

If you don\u2019t have one already, please Sign up for an IBM Cloud account<\/a>.<\/p>\n\n\n\n

This tutorial consists of 6 parts, you can start with part I or any other part, however, the necessary environment is set up in part I.
Part I \u2013 data visualization, preparation, and transformation<\/a>
Part II \u2013 build and evaluate machine learning models by using AutoAI<\/a>
Part III \u2013 graphically build and evaluate machine learning models by using SPSS Modeler flow<\/a>
Part IV \u2013 set up and run Jupyter Notebooks to develop a machine learning model<\/a>
Part V \u2013 deploy a local Python app to test your model<\/a>
Part VI \u2013 monitor your model with OpenScale<\/a><\/p>\n\n\n\n

Deployed models can be biased<\/strong> or become less accurate over time<\/strong>, making precise predictions difficult. In order to trust<\/strong> machine learning models and artificial intelligence, deployed models need to be monitored. This is where Watson OpenScale comes into play, because it helps us with 3 kind of monitors:<\/p>\n\n\n\n

\"\"<\/figure>\n\n\n\n