Good question! Trading off false positives and false negatives is a big part of why we expose a score, rather than just a "yes"/"no". Each site has a different balance.

Most of our customers review each user we flag, and have a human make a final go/no-go decision about whether to accept the transaction. I'd recommend starting with that configuration.

Once that's working, then I think it makes sense to automatically block users who have exceptionally high thresholds. We can help identify a threshold with a low rate of false positives!