Modeling Path-Dependent State Transition by a Recurrent Neural Network

Rating transition models are widely used for credit risk evaluation. It is not uncommon that a time-homogeneous Markov rating migration model deteriorates quickly after projecting repeatedly for a few periods. This is because the time-homogeneous Markov condition is generally not satisfied. For a credit portfolio, rating transition is usually path dependent. In this paper, we propose a recurrent neural network (RNN) model for modeling path-dependent rating migration. An RNN is a type of artificial neural networks where connections between nodes form a directed graph along a temporal sequence. There are neurons for input and output at each time-period. The model is informed by the past behaviours for a loan along the path. Information learned from previous periods propagates to future periods. Experiments show this RNN model is robust.