What to do After Deploying your Model to Production? - Analytics Vidhya

When the standard error of mean drops the red threshold we have determined, an alert would be sent, which would require us to look at the model performance and take necessary action like retraining. Retraining can be done in two different methods, either manual retraining or automatic retraining; manual retraining is far more common, as most teams are apprehensive about retraining their models without human interference. Next, we would look at a deployment done by me in Heroku using flask and python. I worked on a case study project, to provide a demo of the same, I deployed the machine learning model as a web application. The case study was to predict the abuse category based on the description provided by the victim.