← Lyft Interview Insights

Lyft·Data Scientist·Technical Phone Screen·Intermediate

Intermediate
Jun 2026

Summary

Did a Lyft DS interview round focused on ML system design, specifically passenger churn prediction. Pretty standard for this type of role but the data schema angle made it more grounded than the usual open-ended design questions.

Questions Asked (1)

Q1

Given a data schema, how would you build a model to predict whether a passenger will churn in the coming weeks?

System DesignData ModelingProduct Analytics & Metrics
Author's notes

Having the schema handed to you sounds like a gift but it kind of paralyzed me at first because I kept second-guessing which features were actually signal vs noise.

Create a free account to read the full note

AI HintsAI Generated

Suggested Approach

Start by clarifying the schema and defining churn precisely (e.g., no ride in X weeks), then walk through a structured ML pipeline: data exploration, feature engineering, model selection, validation, and deployment. Emphasize how you'd handle class imbalance, temporal validation, and business impact.

Pro tip: Frame churn as a time-dependent problem and use time-based splits rather than random splits to avoid leakage; also discuss how you'd translate model outputs into actionable retention campaigns.

1. Clarify schema and define churn

Ask about available tables (rides, user profile, app events) and define churn operationally, e.g., no ride in the next 4 weeks. Confirm the prediction window and observation window.

2. Explore data and engineer features

Perform EDA to understand distributions and missingness. Create features like ride frequency trends, recency, monetary value, app engagement, and tenure, ensuring they are computed only from data before the prediction point.

3. Select and train models

Choose interpretable baselines (logistic regression) and tree-based models (XGBoost/LightGBM) to handle non-linearity. Address class imbalance with techniques like class weights or resampling, and tune hyperparameters.

4. Validate with time-based splits

Use temporal validation (e.g., train on earlier weeks, validate on later weeks) to mimic production. Evaluate with precision-recall AUC, lift at top decile, and calibration, not just accuracy.

5. Deploy and monitor

Discuss how to productionize the model (batch scoring, API), set up monitoring for drift and performance, and integrate with retention systems to trigger interventions.

Key Points to Mention

  • Define churn clearly and align with business goals (e.g., 4-week inactivity).
  • Feature engineering: recency, frequency, monetary (RFM), trend features, and engagement metrics.
  • Handle class imbalance and use appropriate metrics (PR-AUC, lift).
  • Use time-based validation to prevent leakage and simulate real-world deployment.
  • Consider model interpretability (e.g., SHAP) for stakeholder trust and actionable insights.
  • Discuss deployment, monitoring, and feedback loop with retention campaigns.

AI-generated suggestions, not part of the candidate's original notes. May be inaccurate — verify before relying on them.