Artificial neural networks and foreign exchange : a financial micro-structure approach
Market micro-structure variables provide a novel approach to foreign exchange price determination. More precisely, the order flow has been recognised in literature as a main driver of short-term price dynamics in foreign exchange markets. I present an Artificial Neural Network to improve the estimat...
- Autores:
-
Duque Marulanda, Miguel
- Tipo de recurso:
- Trabajo de grado de pregrado
- Fecha de publicación:
- 2019
- Institución:
- Universidad de los Andes
- Repositorio:
- Séneca: repositorio Uniandes
- Idioma:
- eng
- OAI Identifier:
- oai:repositorio.uniandes.edu.co:1992/45178
- Acceso en línea:
- http://hdl.handle.net/1992/45178
- Palabra clave:
- Cambio exterior
Sistema financiero
Aprendizaje automático (Inteligencia artificial)
Economía
- Rights
- openAccess
- License
- http://creativecommons.org/licenses/by-nc-nd/4.0/
| Summary: | Market micro-structure variables provide a novel approach to foreign exchange price determination. More precisely, the order flow has been recognised in literature as a main driver of short-term price dynamics in foreign exchange markets. I present an Artificial Neural Network to improve the estimation of order flow as an "aggreagtor" of private information. The result yields a significant improvement into a Vector Autoregression model prediction, in terms of the chosen metric, that could imply an empirical backing to the order flow as an "aggregator" of private information theory. |
|---|