Liquidity risk modeling using artificial neural network
A new element of risk, liquidity risk, have flourished along this time taking importance and playing a key role in risk management tools. This has attracted the attention of the scientific community and economic and financial experts. This thesis provides a theoretical introduction and a state of th...
| Autor: | |
|---|---|
| Formato: | tesis de maestría |
| Fecha de publicación: | 2011 |
| País: | España |
| Recursos: | Universitat Politècnica de Catalunya (UPC) |
| Repositorio: | UPCommons. Portal del coneixement obert de la UPC |
| Idioma: | inglés |
| OAI Identifier: | oai:upcommons.upc.edu:2099.1/11151 |
| Acesso em linha: | https://hdl.handle.net/2099.1/11151 |
| Access Level: | acceso abierto |
| Palavra-chave: | Neural networks (Computer science) Expert systems (Computer science) Liquidity risk Risk management tools Economic and financial experts Xarxes neuronals (Informàtica) Sistemes experts (Informàtica) Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Sistemes experts |
| Resumo: | A new element of risk, liquidity risk, have flourished along this time taking importance and playing a key role in risk management tools. This has attracted the attention of the scientific community and economic and financial experts. This thesis provides a theoretical introduction and a state of the art survey of the key elements needed to understand the complexity of the dealt issue. So it provides an study over liquidy risk and its application in market risk being included in market risk measures such as value at risk. Also an study over the behaviour of time series and it explores a relatively new alternative approach to model the liquidity risk using artificial neural networks, mainly approached in focused delay and recurrent neural networks due to their capability to work with time series . In addition in this work have been designed and developed a methodology for the purpose of improving the way to treat time series and as resulting a simple graphical user interface with the intention of make easy the prediction. This work has been developed on the framework Matlab Student Version version R2010a including Neural Network Toolbox 6.0.4. over a laptop with Windows Vista 32 bits, CPU: Intel(R) Core(TM)2 Duo CPU 2.20GHz and RAM: 2038 MB. |
|---|