Pngme's latest Model Explainability document can be found here.
This document outlines methodology, performance and stability of Pngme's risk score prediction. The Central Bank of Kenya does not currently publish or enforce comprehensive regulation on model risk management. This document generally follows guidelines for model risk management as outlined in the US Federal Reserve SR 11-7 Guidelines . Pngme continues to monitor the emerging regulatory space in Kenya, and expects that any model explainability and risk management that complies with SR 11-7 will also meet emergent regulation.
A lift curve shows a model's ability to separate the best borrowers from the worst borrowers.
The x-axis shows a population of borrowers evenly divided among ten groups (deciles), and ranked from the very best scores (left) to very worse scores (right) based on the model's prediction. The y-axis shows the actual observed loan-overdue rate (bad-rate) for each group. The more powerful the model, the greater the separation between bad-rate for the group on the left and the group on the right.