Online Program Home
My Program

Abstract Details

Activity Number: 426
Type: Contributed
Date/Time: Tuesday, August 2, 2016 : 2:00 PM to 3:50 PM
Sponsor: Section on Risk Analysis
Abstract #319157 View Presentation
Title: Alternative Methods to Estimate Major Banks' Residential and Commercial Mortgage Loan Delinquency Rates for CCAR (Stress Testing) 'Baseline' Scenario
Author(s): Vadim Melnitchouk* and Andrey Vashurin
Companies: Metropolitan State University and University of Telecommunications
Keywords: Stress Testing ; delinquency ; Markov Chains model ; steady state ; macroeconomic variables
Abstract:

Federal Reserve Bank is publishing three macroeconomic and financial scenarios to be used in stress testing the CCAR financial institutions. A "baseline" CCAR scenario represents "an expected or median path for the economy and financial markets". In addition each bank is required to design its own scenarios including "baseline" one. Predicting losses under "baseline" scenario can be not quite simple task for each bank. Because delinquency is among critical loan default predictors simple Markov Chains model was developed to predict transitions between "current" and delinquent states for residential mortgage loans using the Federal Financial Institutions Examination Council (FFIEC) data. It assumes that current distribution of delinquent loans can be far from a steady state. Our estimations demonstrated a wide range of delinquent loans percentage at steady state across the CCAR banks. More advanced model with macroeconomic variables was also developed to forecast commercial mortgages delinquency rates.


Authors who are presenting talks have a * after their name.

Back to the full JSM 2016 program

 
 
Copyright © American Statistical Association