Comparative analysis between standard risk measurements and behavioral simulations

thumbnail

Estudiant

Urbano García, Francisco

Tipus de document

Projecte Final de Màster Oficial

Data

2012

rights

Accés obertOpen Access

Editorial

Universitat Politècnica de Catalunya



Resum

This project explores behavioral driven simulations as an alternative to the existing classical methods to calculate the most common risk measurements for financial time series, that is, VaR (value at risk) and Expected Shortfalls. . This Final Master Research Project focuses in a comparative analysis among GARCH family models forecast power and a behavioral based simulation of traders in the stock market. The simulation target is to explain and give insights on why the volatility in financial series behaves the way it does, thus, this simulation goes beyond a mere formal model fitting of the data and tries to explain the mechanics within the data
user

Professorat participant

Arxius