A Novel Methodology for Credit Spread Prediction: Depth-Gated Recurrent Neural Network with Self-Attention Mechanism

<div>Mutual information for selected features. (There is no doubt that the term structure of credit spread is the most important factor to predict credit spread. In order to visualize the importance of the other factors in the diagram, we only examine the importance of the remaining factors here.)</div>

Mathematical Problems in Engineering

fig6

Figure 6

Figure 6: A Novel Methodology for Credit Spread Prediction: Depth-Gated Recurrent Neural Network with Self-Attention Mechanism 