Get startedGet started for free

Best time to start deploying

You were given the task of developing a recommendation engine for a brand new streaming service.

Building the model for this use case will be a challenging process, and just the process of experimentation and tuning can easily preoccupy you.

Then, one day, after several months, you did it! The required performance is achieved, so let's deploy this beauty!

Ok, but where? How?

Reality hits you and you learn the hard way that focusing too much on the development can leave the deployment preparations in a blind spot. This could render all your efforts completely useless, because you can not just deploy any model to any platform, they need to be aligned. In the end it takes you three more months of additional development to make a completely new model package, which is deployment ready.

But now you're wiser and you know that the best moment to start preparing your ML model and app for deployment is:

This exercise is part of the course

MLOps Deployment and Life Cycling

View Course

Hands-on interactive exercise

Turn theory into action with one of our interactive exercises

Start Exercise