Interview Q&A / Machine Learning
Machine Learning interview questions
Supervised vs unsupervised learning, overfitting, metrics and the classic models, explained simply.
Prefer rapid revision? Practise Machine Learning short interview answers →
- A fraud model shows 99% accuracy. Why might it still be useless?
If only 1% of transactions are fraud, a model that always says 'not fraud' scores 99% accuracy while catching zero fraud. On imbalanced data, look at recall, precision, F1 or PR-AUC instead.
BeginnerQuick answer1 min read