End-to-End ML Production Project
Take a churn model from raw data through preprocessing, evaluation, serialization, API inference, and containerisation.
Production project
Customer Churn Prediction Service
A subscription product wants a small inference service that flags customers with elevated churn risk for retention workflows.
Who this is for
- •ML learners who are comfortable in notebooks but have not shipped a model
- •Software engineers moving into ML engineering
How this helps
- •You move from notebook-only ML to an actual service boundary
- •You learn the seams where real ML systems usually break
What you will learn
The capabilities, not just the keywords.
- •Build a reproducible preprocessing and model pipeline
- •Choose evaluation metrics based on business impact
- •Serialize and reload a trained model
- •Expose inference through a FastAPI endpoint
- •Containerise the inference service
Real production project
Customer Churn Prediction Service
A subscription product wants a small inference service that flags customers with elevated churn risk for retention workflows.
What we build
- •Preprocessing pipeline
- •classifier
- •evaluation report
- •saved model artifact
- •prediction API
- •Dockerfile
Stack
- •Python
- •Pandas
- •Scikit-learn
- •FastAPI
- •Docker
Production concerns
- •Training-serving consistency
- •threshold choice
- •schema validation
- •versioning
- •monitoring hooks
Finished deliverables
- •Model pipeline
- •evaluation output
- •inference API
- •Docker setup
- •production-readiness checklist
Prerequisites
Required
- •Basic Python
- •Familiarity with train/test split and a classifier
Helpful, but optional
- •Pandas
- •Scikit-learn
- •basic API knowledge
Before the session
Come ready to build.
- •Python 3.11+
- •Jupyter or VS Code
- •Docker Desktop
- •Git
What to expect
What you get
Something useful after the call ends.
- •Working project
- •evaluation template
- •API contract
- •deployment next steps
Where to go next
Machine Learning → ML Engineering → Production Inference
Every session can be booked independently. If you already know the prerequisite material, skip ahead.
Useful before this
No earlier session is mandatory.
Good next steps
Teaching proof
Review the evidence first.
See workshop delivery, technical projects, and teaching proof before booking.
Ready?
Request ML08: End-to-End ML Production Project
Share your current level and what you want to build. The session can be adapted without changing its core outcome.
Request this sessionFAQ
Can I book only this session?
Yes. Every session is designed to work independently.
Can I bring my own project?
Yes, when it fits the session outcome. We can map the concepts onto your project instead of the default example.
What if I already know part of the topic?
We can move faster through familiar material and spend more time on implementation, failure modes, and production trade-offs.
Is the session recorded?
Recording is not promised by default. Confirm this before the session if you need it.
What should I install?
The preparation section above lists the default setup. You will receive any session-specific setup notes before the call.
Are API or cloud charges included?
No. Any third-party API or cloud usage is paid directly through your own account unless explicitly agreed otherwise.