You are handed an existing binary classifier (predicting churn=1) with the following issues: (a) the feature “month” is encoded as an integer 1–12 and used linearly; (b) continuous features of wildly different scales were not standardized; (c) positives are 3% of the data; (d) model is evaluated by overall accuracy. The business requires Recall ≥ 80% at Precision ≥ 30%. - Identify and explain the modeling mistakes. For month, propose and justify two encodings (e.g., one-hot vs. cyclical sin/cos) and when you’d prefer each. - Describe a training procedure to address scale and imbalance: feature standardization, class-weighted loss vs. resampling (SMOTE vs. undersampling), and how you’d select the weight ratio or sampling rate without biasing validation. - Specify an evaluation protocol: stratified cross-validation, primary metrics (PR AUC, recall@precision≥0.30), calibration assessment, and threshold selection to satisfy the operating point. Include how you’d compute and report confidence intervals for these metrics. - If the dataset is imbalanced across subgroups, define a cost-sensitive or group-weighted objective and the fairness/coverage checks you’d add before deployment. Provide a concrete example of a failure mode you would catch and how you’d mitigate it.

This question evaluates a data scientist's competency in applied supervised learning diagnostics, including feature encoding, feature scaling, class imbalance mitigation, evaluation metric selection, calibration, and fairness-aware objective design.

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.

Diagnose and fix flawed model fit | Google Interview Question

Fixing a Churn Classifier: Encoding, Imbalance, Evaluation, and Fairness

Context

You inherit a binary classifier that predicts churn=1. The current implementation has the following issues: (a) the feature "month" is encoded as an integer 1–12 and used linearly; (b) continuous features of very different scales are not standardized; (c) positives are 3% of the data; (d) model performance is reported by overall accuracy. The business requirement is Recall ≥ 80% at Precision ≥ 30%.

Tasks

Identify and explain the modeling mistakes. For the "month" feature, propose and justify two encodings (e.g., one-hot vs. cyclical sin/cos) and state when you’d prefer each.
Describe a training procedure to address scale and class imbalance, including:
- Feature standardization choices.
- Class-weighted loss vs. resampling (SMOTE vs. undersampling).
- How to select the weight ratio or sampling rate without biasing validation.
Specify an evaluation protocol covering:
- Stratified cross-validation.
- Primary metrics (PR AUC, recall at precision ≥ 0.30).
- Calibration assessment and how to select a threshold that satisfies the operating point.
- How to compute and report confidence intervals for these metrics.
If the dataset is imbalanced across subgroups, define a cost-sensitive or group-weighted objective and the fairness/coverage checks you’d add before deployment. Provide a concrete example of a failure mode you would catch and how you’d mitigate it.

Context

Tasks

Identify and explain the modeling mistakes. For the "month" feature, propose and justify two encodings (e.g., one-hot vs. cyclical sin/cos) and state when you’d prefer each.

Describe a training procedure to address scale and class imbalance, including:

Feature standardization choices.
Class-weighted loss vs. resampling (SMOTE vs. undersampling).
How to select the weight ratio or sampling rate without biasing validation.

Specify an evaluation protocol covering:

Stratified cross-validation.
Primary metrics (PR AUC, recall at precision ≥ 0.30).
Calibration assessment and how to select a threshold that satisfies the operating point.
How to compute and report confidence intervals for these metrics.

If the dataset is imbalanced across subgroups, define a cost-sensitive or group-weighted objective and the fairness/coverage checks you’d add before deployment. Provide a concrete example of a failure mode you would catch and how you’d mitigate it.

Diagnose and fix flawed model fit

Quick Overview

Fixing a Churn Classifier: Encoding, Imbalance, Evaluation, and Fairness

Context

Tasks

Solution

Submit Your Answer to Earn 20XP

Diagnose and fix flawed model fit

Quick Overview

Fixing a Churn Classifier: Encoding, Imbalance, Evaluation, and Fairness

Context

Tasks

Solution

Submit Your Answer to Earn 20XP