Noted. But what to do if product requirements dictate sensitivity and specificity (a common scenario)? If you optimize something like Brier score or calibration instead, test may not meet the requirements even if it is theoretically optimal
Noted. But what to do if product requirements dictate sensitivity and specificity (a common scenario)? If you optimize something like Brier score or calibration instead, test may not meet the requirements even if it is theoretically optimal