Explain and quantify bias-variance tradeoff
Company: Roku
Role: Data Scientist
Category: Machine Learning
Difficulty: medium
Interview Round: Technical Screen
Overview: This question evaluates understanding of the bias–variance tradeoff, the expected test-error decomposition into irreducible noise, bias^2, and variance, and practical model-tuning effects such as regularization and training-set size for models like ridge regression or decision trees.
Read the full Roku Data Scientist interview experience this question came from