You’re asked to predict contract renewal for enterprise customers of a video-conferencing product after a spike in call disconnects. Design a modeling approach: define the label (renewal within the next contract period) and prediction horizon; specify features such as disconnection rate per 1k minutes, percent of meetings affected, time-to-resolution, SLA breaches, support ticket volume, NPS/CSAT, active seats, usage intensity, industry, account tenure, and price/discounts; discuss when logistic regression is preferable to gradient-boosted trees or deep models (interpretability, small-N, linear signal, sparse features, latency constraints) and when complex models are justified; prevent leakage (e.g., features created post-renewal), address class imbalance, consider survival analysis vs binary classification for censored data, and optionally add monotonic constraints; outline evaluation beyond AUROC (PR-AUC for rare churn, calibration curves/Brier score, cohort- and time-split backtests, stability under distribution shift), and compare rank-based vs calibrated thresholding; translate scores into actions with cost–benefit thresholds, expected ROI, and capacity constraints; provide a minimal viable feature set and justify it.

This question evaluates competency in applied machine learning for enterprise churn prediction, testing skills in problem framing, feature engineering, model selection, data hygiene, evaluation metrics, and decisioning within the Machine Learning domain.

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 hard 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.

Predict and act on contract renewal risk | Google Interview Question

Predicting Enterprise Contract Renewal After a Quality Incident

Context

A video-conferencing provider experienced a spike in call disconnects. You need to design a practical modeling approach to predict whether an enterprise customer will renew at their next contract decision point so the company can prioritize retention actions.

Task

Propose a modeling and decisioning plan that covers the following:

Problem Framing
- Define the label (renewal within the next contract period) and the prediction horizon (when predictions are made relative to renewal date).
Features
- Specify and precisely define features such as:
  - Disconnection rate per 1,000 minutes
  - Percent of meetings affected
  - Time-to-resolution (e.g., MTTR)
  - SLA breaches
  - Support ticket volume
  - NPS/CSAT
  - Active seats and usage intensity
  - Industry
  - Account tenure
  - Price/discounts
Modeling Choices
- Discuss when logistic regression is preferable to gradient-boosted trees or deep models (interpretability, small-N, linear signal, sparse features, latency constraints).
- Discuss when more complex models are justified.
- Optionally consider monotonic constraints.
Data Hygiene
- Prevent leakage (e.g., avoid features created post-renewal or after the prediction cutoff).
- Address class imbalance.
- Consider survival analysis vs. binary classification for censored data.
Evaluation
- Go beyond AUROC: include PR-AUC for rare churn, calibration curves/Brier score, cohort- and time-split backtests, and stability under distribution shift (pre/post incident).
- Compare rank-based actioning vs. calibrated thresholding.
Decisioning and Actions
- Translate scores into actions with cost–benefit thresholds, expected ROI, and capacity constraints.
Minimal Viable Feature Set (MVFS)
- Provide a minimal feature subset and justify why it’s sufficient to launch.

Task

Propose a modeling and decisioning plan that covers the following:

Problem Framing

Define the label (renewal within the next contract period) and the prediction horizon (when predictions are made relative to renewal date).

Features

Specify and precisely define features such as:
- Disconnection rate per 1,000 minutes
- Percent of meetings affected
- Time-to-resolution (e.g., MTTR)
- SLA breaches
- Support ticket volume
- NPS/CSAT
- Active seats and usage intensity
- Industry
- Account tenure
- Price/discounts

Modeling Choices

Discuss when logistic regression is preferable to gradient-boosted trees or deep models (interpretability, small-N, linear signal, sparse features, latency constraints).
Discuss when more complex models are justified.
Optionally consider monotonic constraints.

Data Hygiene

Prevent leakage (e.g., avoid features created post-renewal or after the prediction cutoff).
Address class imbalance.
Consider survival analysis vs. binary classification for censored data.

Evaluation

Go beyond AUROC: include PR-AUC for rare churn, calibration curves/Brier score, cohort- and time-split backtests, and stability under distribution shift (pre/post incident).
Compare rank-based actioning vs. calibrated thresholding.

Decisioning and Actions

Translate scores into actions with cost–benefit thresholds, expected ROI, and capacity constraints.

Minimal Viable Feature Set (MVFS)

Provide a minimal feature subset and justify why it’s sufficient to launch.

Predict and act on contract renewal risk

Quick Overview

Predicting Enterprise Contract Renewal After a Quality Incident

Context

Task

Solution

Submit Your Answer to Earn 20XP

Predict and act on contract renewal risk

Quick Overview

Predicting Enterprise Contract Renewal After a Quality Incident

Context

Task

Solution

Submit Your Answer to Earn 20XP