Explainable models of credit losses

Credit risk management is an area where regulators expect banks to have transparent and auditable models, which would preclude the use of more accurate black-box models. Furthermore, opaqueness these models may hide unknown biases that lead unfair lending decisions. In this study, we show do not sacrifice prediction accuracy at cost model transparency be compliant with regulatory requirements. We illustrate by showing predictions credit losses given a can easily explained in terms their inputs. Because are better uncovering complex patterns data, should consider determinants suggested decisions pricing exposures.