Data Science Interview Questions

Bias is error from a model being too simple (underfitting); it doesn’t capture the true pattern. Variance is error from the model being too sensitive to the training set (overfitting). High bias → underfitting; high variance → overfitting. The goal is to find the sweet spot (e.g. via cross-validation, regularization, or tuning model complexity).

Precision: Of all predicted positives, how many are correct? (Minimize false positives.) Recall: Of all actual positives, how many did we find? (Minimize false negatives.) Use precision when false positives are costly (e.g. spam marking good email). Use recall when missing a positive is costly (e.g. disease screening). F1 balances both.