# Translating a Business Metric into an ML Accuracy Metric

Let's say that I'm building a binary classifier for giving loans to consumers. But apart from the standard accuracy metrics I can use, I have a requirement from the business, which wants to be able to "auto-approve" 80% of the loans.

My gut instinct is that this should be 1 - False Positive Rate, but I'm not quite sure.

Any ideas?

A weighted false_positive * loss_on_default metric would seem to be ideal, where you set the probability cutoff of positive class (auto-approve) so that 80% of loans were approved regardless of absolute probability of the prediction. Conceptually this is similar to picking a point on the ROC curve and assessing the algorithm at that point.
I did a quick search for similar metrics, and could not find anything (it is also not something I have done before, so do please test the idea carefully, it is mostly conjecture on my part). There are plenty of metrics in e.g. SciKit learn however that take an array sample_weight that does something similar - e.g. Sklearn's Zero-One loss is pretty close except it will include false negatives as well.