Abstract
Due to the six unreasonable assumptions companioned with the Black-Scholes options pricing model (BSM), which often make the miss-pricing result because of the difference of market convention in practical. This study try to combine the BSM and extended Kalman filters-based artificial neural networks (EKF-ANN) to deal with the limitation of consideration of the influences from many unexpected real world phenomena. 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 with examined the forecasting accuracy between the BSM-based kernel machines (KM-BSM) and the BSM-based EKF-ANN (EKF-ANN-BSM). From the evidence of Taiwan Warrants market, we found that the performance indicates the KM is superior to the others, and the hybrid EKF-ANN-BSM framework is also better than the pure EKF-ANN. The results show that the KM-BSM and hybrid model could significantly reduce the normalized root-mean-square-errors (NRMSE) of forecasting, it helps to provide an alternative way to refine the options valuation.
Original language | English |
---|---|
Title of host publication | Proceedings of the 9th Joint Conference on Information Sciences, JCIS 2006 |
DOIs | |
Publication status | Published - 2006 Dec 1 |
Event | 9th Joint Conference on Information Sciences, JCIS 2006 - Taiwan, ROC, Taiwan Duration: 2006 Oct 8 → 2006 Oct 11 |
Publication series
Name | Proceedings of the 9th Joint Conference on Information Sciences, JCIS 2006 |
---|---|
Volume | 2006 |
Other
Other | 9th Joint Conference on Information Sciences, JCIS 2006 |
---|---|
Country | Taiwan |
City | Taiwan, ROC |
Period | 06/10/8 → 06/10/11 |
Fingerprint
Keywords
- Black-Scholes
- Extended Kalman filters
- Kernel machines
- Neural networks
- Warrants
ASJC Scopus subject areas
- Engineering(all)
Cite this
Warrants price forecasting using kernel machine & EKF-ANN : A comparative study. / Wang, Hsing Wen; Wang, Jian Hong; Dong, Tse-ping; Hsu, Sheng Hsun.
Proceedings of the 9th Joint Conference on Information Sciences, JCIS 2006. 2006. CIEF-235 (Proceedings of the 9th Joint Conference on Information Sciences, JCIS 2006; Vol. 2006).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - Warrants price forecasting using kernel machine & EKF-ANN
T2 - A comparative study
AU - Wang, Hsing Wen
AU - Wang, Jian Hong
AU - Dong, Tse-ping
AU - Hsu, Sheng Hsun
PY - 2006/12/1
Y1 - 2006/12/1
N2 - Due to the six unreasonable assumptions companioned with the Black-Scholes options pricing model (BSM), which often make the miss-pricing result because of the difference of market convention in practical. This study try to combine the BSM and extended Kalman filters-based artificial neural networks (EKF-ANN) to deal with the limitation of consideration of the influences from many unexpected real world phenomena. 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 with examined the forecasting accuracy between the BSM-based kernel machines (KM-BSM) and the BSM-based EKF-ANN (EKF-ANN-BSM). From the evidence of Taiwan Warrants market, we found that the performance indicates the KM is superior to the others, and the hybrid EKF-ANN-BSM framework is also better than the pure EKF-ANN. The results show that the KM-BSM and hybrid model could significantly reduce the normalized root-mean-square-errors (NRMSE) of forecasting, it helps to provide an alternative way to refine the options valuation.
AB - Due to the six unreasonable assumptions companioned with the Black-Scholes options pricing model (BSM), which often make the miss-pricing result because of the difference of market convention in practical. This study try to combine the BSM and extended Kalman filters-based artificial neural networks (EKF-ANN) to deal with the limitation of consideration of the influences from many unexpected real world phenomena. 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 with examined the forecasting accuracy between the BSM-based kernel machines (KM-BSM) and the BSM-based EKF-ANN (EKF-ANN-BSM). From the evidence of Taiwan Warrants market, we found that the performance indicates the KM is superior to the others, and the hybrid EKF-ANN-BSM framework is also better than the pure EKF-ANN. The results show that the KM-BSM and hybrid model could significantly reduce the normalized root-mean-square-errors (NRMSE) of forecasting, it helps to provide an alternative way to refine the options valuation.
KW - Black-Scholes
KW - Extended Kalman filters
KW - Kernel machines
KW - Neural networks
KW - Warrants
UR - http://www.scopus.com/inward/record.url?scp=33847767031&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=33847767031&partnerID=8YFLogxK
U2 - 10.2991/jcis.2006.99
DO - 10.2991/jcis.2006.99
M3 - Conference contribution
AN - SCOPUS:33847767031
SN - 9078677015
SN - 9789078677017
T3 - Proceedings of the 9th Joint Conference on Information Sciences, JCIS 2006
BT - Proceedings of the 9th Joint Conference on Information Sciences, JCIS 2006
ER -