Credit Risk Modeling

We offer implementation and consulting services focused on the design and development of challenger credit risk machine learning models. These models are used for benchmarking purposes such as testing the primary models for accuracy and robustness as well as for loan underwriting. Our expertise ranges in the following, but not limited to, modeling domains: Probability of Default (PD), Exposure at Default (EAD), Loss given Default (LGD), and Expected Credit Loss (ECL).

Model Risk Management

Quantitative models within banks produce vast amount of predictions, on a daily basis, to inform regulatory, internal capital allocations and limit monitoring. A small fraction of these predictions are extreme, and knocked out of the normal distribution of results by a quirk of the computation cycle or faulty data inputs. We can help model validators in the ongoing monitoring of internal and regulatory models to police the outputs of primary models and determine whether those models are performing within acceptable tolerances or drifting from their original purpose i.e. generating anomalous projections.