Categorical machine learning microservice

Job ID: 33792753

Budget: €250 – €750 EUR

I need a probability estimator running as a microservice with high availability.
The training set is 150 million records, unbalanced, all features are categorical, some categories with high cardinality. The model needs to be updated daily.
I'm thinking Catboost + FastAPI + Docker / Kubernetes, but I'm open to suggestions
Related categories: Python Machine Learning (ML) Kubernetes FastAPI