Google Machine Learning Interview Questions
Master your tech interview with our curated database of real questions from top companies.
Build Model to Predict Customer Contract Renewal
Predicting Enterprise Customer Renewal for Google Meet You are tasked with designing a model to predict whether an enterprise customer will renew thei...
Compare Logistic Regression and Random Forest in Limited Data Scenarios
Model Selection for Binary Classification with Limited Data and Potential Non-Linearities Scenario You are designing a binary classifier with limited ...
Engineer Features to Enhance Smartphone Battery Life Prediction
Battery Life Prediction with Sparse History Problem You are given sparse discharge traces that record battery percentage over elapsed time for prior u...
Identify and Fix Predictive Model Performance Gaps
Model Review: Month Encoding, Feature Scaling, and Imbalanced Data Context You are auditing an existing predictive model for operational performance. ...
Build Classifier: Evaluate with AUROC for Imbalanced Data
Detecting Dead Links: Build and Evaluate a Classifier Scenario You have a dataset of 1,000 URLs labeled as good (alive) or bad (dead). The classes are...
Detect Overfitting or Underfitting in Logistic Regression Models
Logistic Regression Bias–Variance in High‑Dimensional Ads Prediction Scenario You are building a large‑scale binary classifier (e.g., click/conversion...
Explain Linear Regression to Non-Technical Stakeholders
Scenario You are explaining core machine learning concepts to non-technical stakeholders during a project discussion. Questions 1. Explain linear regr...
Address Overfitting in Supervised Learning Models
Bias–Variance Trade-off and Reducing a Train–Test Performance Gap Scenario You are evaluating a supervised learning model and observe that training ac...
Adjust YouTube Ad Scores Using Mixed-Effects Linear Regression
Scenario - 100 reviewers each rate the same 100 YouTube ads on a 1–10 scale. - Ratings may be systematically higher or lower for some reviewers (lenie...
Address Overfitting with L1 Regularization in Regression
Linear Regression with Many Predictors and Few Observations Scenario You fit an ordinary least squares (OLS) linear regression with 500 predictors (fe...
Build and evaluate illegal-video classifier
End-to-End ML System Design: Flag Illegal YouTube Videos You are tasked with designing a production ML system to detect and triage potentially illegal...
Find companies similar to a given client
System Design: Retrieve Top-20 Most Similar Companies for Sales Prospecting You are given an anchor client (e.g., The Coca‑Cola Company). Design a sys...
Estimate b when features exceed samples
Consider the linear model y = Xb + ε with X ∈ R^{n×(m+1)} including an intercept. a) Derive the OLS estimator b̂ = (XᵀX)^{-1}Xᵀy, stating the rank con...
Build and evaluate bad-link classifier
You have 1,000 URLs labeled as bad or good and a much larger unlabeled pool, with bad links rare. Design features and train a logistic regression. Exp...
Build and evaluate a full ML pipeline
You must predict both (1) probability that a user will spend >$0 in the next 7 days (classification) and (2) expected spend in the next 7 days (regres...
Predict and act on contract renewal risk
Predicting Enterprise Contract Renewal After a Quality Incident Context A video-conferencing provider experienced a spike in call disconnects. You nee...
Decide between two vendors under constraints
You have two third‑party search vendors, A and B, plus historical order‑level data: lead_time_days, unit_price, on_time_rate, defect_rate, min_order_q...
Explain logistic regression vs forests and boosting
Technical Screen — Machine Learning Answer all parts precisely. 1) Binary logistic regression: model, loss, gradient, convexity - Define the model: p(...
Diagnose and fix flawed model fit
Fixing a Churn Classifier: Encoding, Imbalance, Evaluation, and Fairness Context You inherit a binary classifier that predicts churn=1. The current im...
Design a battery-life predictor and cold-start strategy
Smartphone Time-to-Empty (TTE) Prediction — Baseline, Features, Cold Start, Evaluation, and Monitoring Context You are building a per-device predictor...