Skills application
Predicting customer churn
In this skills application, you will apply your knowledge of variable characterisation, transformation techniques and feature selection by designing an end-to-end workflow for a churn prediction problem.
The goal is to choose transformations that reveal the strongest signals while balancing interpretability, noise reduction and model performance.

Success criteria
To successfully complete this activity, write a report of up to 1,800 words that explains:
- What the key drivers behind churn are
- What features you engineered to reveal those insights
- How you can be confident in the quality of those insights
Stakeholder challenge
A stakeholder has noticed that a model trained on the raw data appears to produce higher accuracy. Part of your task is to explain why a model built on engineered features may still be the better business solution.
Instructions
Launch the Skillable lab and work through techniques for engineering new features. At the end of the lab, you will build a model using engineered features to predict customer churn.
Important access information
Please set aside 30 uninterrupted minutes before opening the lab. Your attempt expires after 30 minutes, and you are limited to a maximum of five attempts within 90 days from your initial attempt.