Evaluate New Model's Performance Against Existing System

Quick Overview

This interview question evaluates core ML concepts, assumptions, math intuition, training/evaluation trade-offs, and practical failure modes in a realistic interview setting. A strong answer for Evaluate New Model's Performance Against Existing System states assumptions, handles edge cases, explains trade-offs, and shows how to validate the result clearly.

Evaluate New Model's Performance Against Existing System

Company: Meta

Role: Data Scientist

Category: Machine Learning

Difficulty: medium

Interview Round: Technical Screen

##### Scenario A new machine-learning model flags harmful posts; leadership wants evidence it outperforms the old system. ##### Question How would you evaluate the performance of the new harmful-content detection model versus the existing model or no model? Describe both offline evaluation (confusion matrix metrics) and online A/B testing approaches, addressing precision-recall trade-offs. ##### Hints Mention metrics (precision, recall, F1, ROC), calibration, business KPIs, guardrails, and experiment design.

Quick Answer: This interview question evaluates core ML concepts, assumptions, math intuition, training/evaluation trade-offs, and practical failure modes in a realistic interview setting. A strong answer for Evaluate New Model's Performance Against Existing System states assumptions, handles edge cases, explains trade-offs, and shows how to validate the result clearly.

|Home/Machine Learning/Meta
Meta logo
Meta
Aug 4, 2025, 10:55 AM
mediumData ScientistTechnical ScreenMachine Learning
4
0

Evaluate New Model's Performance Against Existing System

Scenario

You are evaluating a new machine-learning model that detects harmful content on a large consumer platform. Leadership needs evidence that the new model outperforms the existing model, and to understand trade-offs between catching more harmful posts and avoiding over-removal of benign posts.

Task

Design a comprehensive evaluation plan to compare the new model against:

  • the existing (production) model, and
  • optionally, a minimal/no-model baseline (only if safe via safeguards).

Address both:

  1. Offline evaluation using labeled data and confusion-matrix-based metrics.
  2. Online A/B testing and experiment design.

Make the precision–recall trade-offs explicit, and connect model metrics to business outcomes.

Requirements

  • Define key metrics: precision, recall, F1/Fβ, ROC-AUC, PR-AUC, calibration (Brier score, reliability), threshold-specific metrics.
  • Describe dataset design, label quality, and class imbalance handling.
  • Propose thresholding/triage policies (e.g., auto-remove vs. send-to-review).
  • Outline online experiment design: unit of randomization, triggers, guardrails, primary/secondary KPIs, safety and ethical constraints.
  • Include validation steps, power/duration considerations, and guardrails for false positives and user impact.

Constraints & Assumptions

  • Preserve the scope, facts, inputs, and requested outputs from the prompt above.
  • If the prompt leaves a detail unspecified, state a reasonable assumption before relying on it.
  • Keep the answer interview-ready: concise enough to present, but concrete enough to implement or evaluate.

Clarifying Questions to Ask Guidance

  • Clarify the task, data shape, labels, constraints, and evaluation metric.
  • State assumptions behind the math or modeling technique you choose.
  • Connect theory to practical training, debugging, and deployment implications.

What a Strong Answer Covers Guidance

  • Correct definitions and formulas where the prompt requires them.
  • A practical explanation of how the method behaves on real data.
  • Trade-offs, failure modes, diagnostics, and mitigation strategies.
  • Evaluation choices that match the product or modeling objective.

Follow-up Questions Guidance

  • How would noisy labels, class imbalance, or distribution shift affect the answer?
  • What would you monitor after deployment?
  • Which baseline would you compare against first?
Loading comments...