Rank-Based Error Tracking for Agency MBS Prepayment Models

Jun 30, 2020

Model testing, also called error tracking, is a key requirement for collateral behavior forecasting models in securitized products. The high dimensionality and statistical noise associated with agency mortgage-backed securities prepayment behavior makes error tracking a complex task. The traditional method focuses on a single dimension, and does not provide a clear measure of model accuracy and effectiveness.

A rank-based error-tracking methodology provides an efficient and comprehensive approach to measure model performance. It provides a definition of accuracy which allows a clear comparison among models. This is superior to the existing one-dimensional method and other supplement methods. We discuss these issues as well as applicable statistical theory and potential applications. ©2020 Pageant Media. Republished with permission of IPR Journal, from “Rank-Based Error Tracking for Agency MBS Prepayment Models.” Jiawei “David” Zhang. Vol. 30, No. 1, 2020.