Analysis of day-effect in the Colombian stock market using self-organizing maps
Fecha
Director
Enlace al recurso
DOI
ORCID
Google Scholar
Cvlac
gruplac
Descripción Dominio:
Título de la revista
ISSN de la revista
Título del volumen
Editor
Universidad Santo Tomás. Seccional Bucaramanga
Compartir
Resumen
En este artículo se presenta un modelo de mapa autoorganizado de Kohonen (SOM), para encontrar una relación entre el día de la semana de la primera y segunda quincena del mes con el valor COLCAP, el cual corresponde al índice de referencia del mercado accionario colombiano. Adicionalmente, se describen los datos empleados, la configuración del SOM y los resultados de su entrenamiento. Utilizando la visualización por componentes del SOM se revelan gráficamente, respecto al día semanal en cada quincena, las predominancias que existen en el valor del retorno del índice COLCAP.
In this article is presented a model of Kohonen’s Self-Organizing Map (SOM), used to find a relation between weekday in the first and the second fortnight with the daily return of index COLCAP, the reference index of Colombian stock market. In addition it is described data used, the configuration used in the SOM and its training results. Using visualizations by SOM components it is revealed graphically, regarding weekday on each fortnight, the existing predominances in the return value of COLCAP index.
In this article is presented a model of Kohonen’s Self-Organizing Map (SOM), used to find a relation between weekday in the first and the second fortnight with the daily return of index COLCAP, the reference index of Colombian stock market. In addition it is described data used, the configuration used in the SOM and its training results. Using visualizations by SOM components it is revealed graphically, regarding weekday on each fortnight, the existing predominances in the return value of COLCAP index.
Abstract
Idioma
Palabras clave
Mapas autoorganizados, mercado accionario colombiano, quincena, retorno diario, Colombian stock market, daily return, fortnight, self-organizing maps
Citación
Colecciones
Licencia Creative Commons
Copyright (c) 2018 ITECKNE