Mortgage Markets in the Age of AI

This book explains the US mortgage market in plain language first, then the mathematics, then the AI now taking over the work. It follows eight people through the life of one loan - Jack the borrower, Maya the loan officer, Priya the servicer, Benny the dealer, Elena the investor, Peter the quant, Melissa the examiner, and Simon the retail saver - and every formula arrives attached to whoever uses it.Nine chapters carry one thirty-year payment stream from a kitchen table to a trading desk. The early chapters build the mortgage: amortization, underwriting and credit, pooling, the prepayment conventions (SMM, CPR, PSA), and why the 2007 loans defaulted together. The middle chapters add the desk's machinery: SOFR discounting, DV01 and key rate durations, Itô's lemma and short-rate models, the prepayment option as a receiver swaption, and option-adjusted spread.Machine learning runs alongside from the first chapter: each chapter before the last ends its theory with a bridge from the classical method to the learned one, from loan-level feature vectors and survival networks to neural SDEs. The last chapter puts it to work where it pays - hybrid models that keep an explainable baseline and learn only the residual, neural pricing surrogates that compute OAS and DV01 in real time, GPU numerics - and covers the governance a model validator will demand before any of it runs with money behind it.Every chapter ends with a retail window, because agency MBS is probably already in your bond fund. Key results are measured on Fannie Mae's loan-level data, and every function the book names is in mortgagekit, its open-source Python companion.