A 10,000-user company has a rare account-takeover event rate of 1%. A detection model catches 90% of real takeovers and has 95% specificity. How should the team interpret the alert queue? Base-rate walkthrough: population -> real events -> true positives -> false positives -> alert mix The common shortcut is to hear '95% specific' or '95% accurate' and assume most alerts are true incidents. That skips the fact that the non-event group is much larger. Start with the base rate 1% of 10,000 users means about 100 real takeover events and 9,900 non-events. The base rate creates the starting counts.…
Read the full lesson
Sign up free: one personalized lesson every day, matched to your role and goals.
Already have an account? Sign in