Banking Revolution

<p>Banks accredited by their regulator to use the Advanced Internal Ratings Based (A-IRB)</p><p>approach are required to provide their own estimates for calculating their minimum credit</p><p>capital; these estimates rely on statistical and analytical models to predict Probability of</p><p>Default (PD) Loss Given Default (LGD) and Exposure at Default (EAD). This thesis</p><p>focusses on estimating EAD for banks granting revolving loans to large corporates and</p><p>leverages the Global Credit Data (GCD) database.</p><p>This thesis briefly discusses why risk management particularly credit risk management is</p><p>important for banks and we survey the existing EAD modelling literature which to date</p><p>has had less focus than PD and LGD modelling.</p><p>Our prosed methodology models both loan balance at default (EAD) and changes in loan</p><p>limit at default as random variables modelling their joint dynamics via a two stage model</p><p>- the first stage estimates the probability that limits decrease while the second stage</p><p>estimates EAD conditional on changing limits. To the best of our knowledge our approach</p><p>is the first to estimate EAD and changes in loan limit directly for large corporate revolving</p><p>facilities using the GCD database.</p><p>Our model suggests that the key drivers of EAD include: limit; balance; utilisation; risk</p><p>rating; and time to maturity. We also find evidence that banks actively manage limits in</p><p>the lead up to default and that these changes in limits have substantial effects on the</p><p>outcomes of realised EAD.</p>