Posterior probability given model accuracy

Q: Posterior probability given model accuracy

This question evaluates a candidate's understanding of Bayesian inference and conditional probability as applied to binary classifiers, with emphasis on interpreting sensitivity, specificity and base-rate effects.

Q: How do I approach Analytics & Experimentation interview questions?

Analytics & Experimentation questions require understanding of core concepts and practice. PracHub provides solutions with explanations to help you master analytics & experimentation interviews.

Question

Security Classification: Posterior Probability When Flagged

Context

You are evaluating a binary classifier that flags potentially bad users. Assume:

Base rate of bad users: P(Bad) = 5%.
Symmetric 95% accuracy: sensitivity (true positive rate) = 95% and specificity (true negative rate) = 95%.

Question

Using Bayes' theorem, compute the posterior probability that a user is truly bad given they are flagged by the model: P(Bad | Flagged).

Posterior probability given model accuracy

Security Classification: Posterior Probability When Flagged

Context

Question

Solution

Comments (0)