How do I approach Machine Learning interview questions?

Machine Learning questions require understanding of core concepts and practice. PracHub provides solutions with explanations to help you master machine learning interviews.

What difficulty level is this interview question?

This is a medium difficulty Machine Learning question, commonly asked during Technical Screen rounds at Google.

What role is this question designed for?

This question is commonly asked for Data Scientist candidates at Google during technical interviews.

Build Model to Predict Customer Contract Renewal

Quick Overview

This question evaluates a data scientist's competency in end-to-end supervised machine learning for enterprise contract renewal prediction, covering problem framing, target definition and sampling windows, feature engineering, model choice, and model evaluation.

Predicting Enterprise Customer Renewal for Google Meet

You are tasked with designing a model to predict whether an enterprise customer will renew their Google Meet contract.

Requirements

End-to-end approach
- Define the sampling timeline (observation/feature window, blackout period, prediction window).
- Precisely define the target (what counts as a “renewal” vs. “churn/downgrade”).
Feature engineering
- Which features would you create and why? Consider product usage, account context, pricing/contract terms, and customer experience.
Model choice
- When is logistic regression sufficient?
- When would you prefer more complex models (e.g., Gradient Boosted Machines, Neural Networks)?
Evaluation and comparison
- How would you evaluate and compare models (AUC, calibration, business lift, feature importance, interpretability vs. performance trade-offs)?

Hints: Cover sampling window, target definition, feature importance, calibration, AUC, business lift, and interpretability vs. performance trade-off.

Quick Overview

Requirements

End-to-end approach

Define the sampling timeline (observation/feature window, blackout period, prediction window).
Precisely define the target (what counts as a “renewal” vs. “churn/downgrade”).

Feature engineering

Which features would you create and why? Consider product usage, account context, pricing/contract terms, and customer experience.

Model choice

When is logistic regression sufficient?
When would you prefer more complex models (e.g., Gradient Boosted Machines, Neural Networks)?

Evaluation and comparison

How would you evaluate and compare models (AUC, calibration, business lift, feature importance, interpretability vs. performance trade-offs)?

Hints: Cover sampling window, target definition, feature importance, calibration, AUC, business lift, and interpretability vs. performance trade-off.

Build Model to Predict Customer Contract Renewal

Quick Overview

Predicting Enterprise Customer Renewal for Google Meet

Requirements

Solution

Submit Your Answer

Build Model to Predict Customer Contract Renewal

Quick Overview

Predicting Enterprise Customer Renewal for Google Meet

Requirements

Solution

Submit Your Answer