Title :
Using heavy-tailed distributions to stress-test kernel methods for segregating the firms that are likely to survive
Author :
Hosseinizadeh, Pouyan ; Guergachi, Aziz
Author_Institution :
Mech. & Ind. Eng. Dept., Ryerson Univ., Toronto, ON, Canada
Abstract :
While kernel-based learning methods have emerged during the last two decades as major tools to effectively manage uncertainty, heavy-tailed distributions remain a major challenge for modelers who aim to predict the future behavior of complex systems. In this article, Weibull distribution has been used to stress-test kernel-based methods and study more specifically the impact of heavy-tailed distributions on the performance of Fisher kernels in identifying the potential for collapse of an enterprise based on its stock price.
Keywords :
Weibull distribution; corporate modelling; learning (artificial intelligence); Fisher kernels; Weibull distribution; complex systems; enterprise; heavy-tailed distributions; kernel-based learning; stock price; stress-test kernel methods; Computational modeling; Gaussian distribution; Kernel; Learning systems; Mathematical model; Predictive models; Probability distribution; Statistical learning; Uncertainty; Weibull distribution; Fisher kernel; Weibull distribution; financial time series; heavy-tailed distributions; modelling; prediction;
Conference_Titel :
Systems, Man and Cybernetics, 2009. SMC 2009. IEEE International Conference on
Conference_Location :
San Antonio, TX
Print_ISBN :
978-1-4244-2793-2
Electronic_ISBN :
1062-922X
DOI :
10.1109/ICSMC.2009.5346298