Dataford
Interview QuestionsInterview GuidesExperiencesMock InterviewsPricing
Get started

Assessing Model Overfitting

MediumModel Evaluation00:00
F
Five9
Your interviewer · Data Scientist
In session
F
Interviewer

Welcome to your interview for the Data Scientist role at Five9.

The question is on your right: Assessing Model Overfitting. Take a moment with it first.

Talk your thinking through with me if you like - when you're confident, submit your answer and I'll grade it like a real screen. You have three graded attempts to score 7/10 or better.

Only Submit answer is graded - discussion is free practice.

Problem

Scenario

You've trained a model that looks strong on the data used during development, but the team is worried the performance may not hold up on unseen data. You need to explain how you would tell whether the model is overfitting.

Question

How would you assess whether a model is overfitting?

What to Look For

  • Gap between training and validation metrics
  • Cross-validation mean and variance
  • Performance as model complexity increases
  • Calibration or log loss deterioration out of sample