Agency MBS Prepayment Model Using Neural Networks

Abstract

The authors apply deep neural networks, a type of machine learning method, to model agency mortgage-backed security (MBS) 30-year, fixed-rate pool prepayment behaviors. The neural networks model (NNM) is able to produce highly accurate model fits to the historical prepayment patterns as well as accurate sensitivities to economic and pool-level risk factors. These results are comparable with model results and intuitions obtained from a traditional agency pool-level prepayment model that is in production and was built via many iterations of trial and error over many months and years. This example shows NNM can process large datasets efficiently, capture very complex prepayment patterns, and model large group of risk factors that are highly nonlinear and interactive. The authors also examine various potential shortcomings of this approach, including nontransparency/“black-box” issues, model overfitting, and regime shift issues.