Deep Learning-Based Method for Computing Initial Margin †
![Thumbnail](/dspace/bitstream/handle/2183/29314/Perez_Villarino_Joel_2021_Deep_Learning-Based_Method.pdf.jpg?sequence=5&isAllowed=y)
Use este enlace para citar
http://hdl.handle.net/2183/29314Colecciones
Metadatos
Mostrar el registro completo del ítemTítulo
Deep Learning-Based Method for Computing Initial Margin †Fecha
2021Cita bibliográfica
Pérez Villarino, J.; Leitao Rodríguez, Á. Deep Learning-Based Method for Computing Initial Margin. Eng. Proc. 2021, 7, 41. https://doi.org/10.3390/engproc2021007041
Resumen
[Abstract] Following the guidelines of the Basel III agreement (2013), large financial institutions are forced to incorporate additional collateral, known as Initial Margin, in their transactions in OTC markets. Currently, the computation of such collateral is performed following the Standard Initial Margin Model (SIMM) methodology. Focusing on a portfolio consisting of an interest rate swap, we propose the use of Artificial Neural Networks (ANN) to approximate the Initial Margin value of the portfolio over its lifetime. The goal is to find an optimal configuration of structural hyperparameters, as well as to analyze the robustness of the network to variations in the model parameters and swap features.
Palabras clave
Computational finance
Colateral
Initial margin
Deep learning
Colateral
Initial margin
Deep learning
Descripción
Presented at the 4th XoveTIC Conference, A Coruña, Spain, 7–8 October 2021
Versión del editor
Derechos
Atribución 3.0 España