Warrants Price forecasting using kernel machine and EKF-ANN: a comparative study

DOI

10.2991/jcis.2006.99How to use a DOI?

Keywords

Black-Scholes, SVM, GARCH, ANFIS, Derivatives

Abstract

The Black-Scholes options pricing model (BSM) is limited by the influences of many unexpected real world phenomena caused due to its six unreasonable assumptions, which often make the miss-pricing result because of the difference of market convention in practical. If we were to soundly take these phenomena into account, the pricing error could be reduced. In this paper, we try to make a comparative study between the support vector machines (SVM) and the Extended Kalman Filters-based Artificial Neural Networks, named adaptive neural-based fuzzy inference system (ANFIS). The performance indicates the SVM method is better than the ANFIS. Using evidence from the warrants market in Taiwan, it helps to provide an alternative way to refine the options valuation.

Copyright

© 2006, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Hsing-Wen Wang
AU  - JIAN-HONG WANG
AU  - TSE-PING DONG
AU  - SHENG-HSUN HSU
PY  - 2006/10
DA  - 2006/10
TI  - Warrants Price forecasting using kernel machine and EKF-ANN: a comparative study
BT  - Proceedings of the 9th Joint International Conference on Information Sciences (JCIS-06)
PB  - Atlantis Press
SN  - 1951-6851
UR  - https://doi.org/10.2991/jcis.2006.99
DO  - 10.2991/jcis.2006.99
ID  - Wang2006/10
ER  -