Meta is evaluating a lightweight classifier that flags potentially bad Instagram Reels before ranking. The model is being considered as an upstream filter in the AARRR funnel because false alarms can suppress healthy creator distribution, while misses can hurt integrity.
A classifier used on Instagram Reels has 95% true positive rate and 95% true negative rate for detecting bad content. The underlying prevalence of actually bad Reels is only 1%. You need to determine the probability that a Reel is actually bad given that the classifier predicted bad.
| Metric | Value |
|---|---|
| Base rate of actually bad Reels | 1.0% |
| True positive rate, | 95.0% |
| True negative rate, | 95.0% |
| False positive rate, | 5.0% |
| Population size for intuition check | 1,000,000 Reels |
Here, means actually bad, means actually good, and means predicted bad.