Serve Data Models with MLFlow in Production

Too Long; Didn't Read

MLFlow allows serving data models as REST API without the complicated setup. For organizations looking for a way to ‘democratize’ data science, it is a must that data models are accessible to the enterprise. There are other solutions out there to serve data models which is a very common problem for data scientists. We used anaconda3 to setup the environment and at least 1GB of RAM is needed to get R running with MLFlow in AWS LightSail. For Python-based models, MLFLow supports deploying to SageMaker.