International Journal of Systems Science

jiggerluncheonΤεχνίτη Νοημοσύνη και Ρομποτική

19 Οκτ 2013 (πριν από 3 χρόνια και 7 μήνες)

102 εμφανίσεις

This article was downloaded by: [National Taipei University of Technology]
On: 04 June 2012, At: 18:17
Publisher: Taylor & Francis
Informa Ltd Registered in England and Wales Registered Number: 1072954 Registered office: Mortimer
House, 37-41 Mortimer Street, London W1T 3JH, UK
International Journal of Systems Science
Publication details, including instructions for authors and subscription
Neural network forecasting of an opening cash
price index
Tian-Shyug Lee & Chih-Chou Chiu
Available online: 26 Nov 2010
To cite this article: Tian-Shyug Lee & Chih-Chou Chiu (2002): Neural network forecasting of an opening cash price
index, International Journal of Systems Science, 33:3, 229-237
To link to this article:
Full terms and conditions of use:
This article may be used for research, teaching, and private study purposes. Any substantial or
systematic reproduction, redistribution, reselling, loan, sub-licensing, systematic supply, or distribution
in any form to anyone is expressly forbidden.
The publisher does not give any warranty express or implied or make any representation that the
contents will be complete or accurate or up to date. The accuracy of any instructions, formulae, and
drug doses should be independently verified with primary sources. The publisher shall not be liable for
any loss, actions, claims, proceedings, demand, or costs or damages whatsoever or howsoever caused
arising directly or indirectly in connection with or arising out of the use of this material.
International Journal of Systems Science,2002,volume 33,number 3,pages 229±237
Neural network forecasting of an opening cash price index
Tian-Shyug Leey* and Chih-Chou Chiuz
The study investigates the information content of SGX-DT Nikkei 225 futures prices
during the non-cash-trading (NCT) period using an arti®cial neural network model.
The cash market closing index,the futures prices froma period in the same trading day
and on the following trading day are utilized to determine the appropriate input nodes of
a back propagation neural network model in forecasting the opening cash price index.
Sensitivity analysis is ®rst employed to address and solve the issue of ®nding the
appropriate network topology.Extensive studies are then performed on the robustness
of the constructed network by using di￿erent training and testing sample sizes.The
e￿ectiveness of the method is demonstrated on data from a 6-month historical record
(1998±99).Analytic results demonstrate that the proposed neural network model out-
performs a neural network model with the previous day’s closing index as the input node
and the random walk model forecasts.It,therefore,indicates that there is valuable
information involved in futures prices during the NCT period that can be used to
forecast the opening cash market price index.
It is a common practice that the daily trading period of
an index futures contract ends later and begins earlier
than that of its underlying spot market.In this study,the
period between daily close and the subsequent opening
of the cash index trading is de®ned as the non-cash-
trading (NCT) period.Valuable information should be
obtained through the analysis of the NCT period of the
futures market and should contribute to the success of
implementing proper investment decisions for the
underlying spot market.For the SGX-DT (Singapore
Exchange-Derivatives Trading Ltd) Nikkei 225 futures
contracts and its underlying cash,there are two trading
sessions in each trading day.For futures (cash) trading,
the morning session is from 07:55 to 10:15 (from 08:00
to 10:00) and the afternoon session is from 11:15 to
14:25 (from 11:30 to 14:00),Singapore time.Therefore,
the information contents of NCT (from 14:00 to 14:25 in
each trading day and from 07:55 to 08:00 in the fol-
lowing trading day) futures prices are analysed in this
study.And since the world’s leading European and
American stock markets start the daily trading after
the Nikkei 225 futures and cash markets close and end
the daily trading before the Nikkei 225 markets open,it
is therefore assumed that the new information of the
world’s leading markets will be re¯ected in the Nikkei
225 index futures prices ®rst before it reaches the cash
market.Following the above argument,this research
investigates the information content of SGX-DT
Nikkei 225 futures prices during the NCT period.In
this research,the neural networks approach is proposed
to build the model in forecasting the opening cash
market price index.The cash market closing index at
14:00,the futures prices from 14:00 to 14:25 in the
same trading day,and the futures prices at 07:55 in
the following trading day are utilized to determine the
appropriate input nodes of the backpropagation neural
network (BPNN) model in forecasting the 08:00 opening
cash market price index.Note that we cannot use the
popular ARIMA forecasting technique here since
ARIMA is an univariate model that only uses the his-
torical data to make inferences about the variable we are
interested in.And in this study,we will be using both the
cash index and futures index in predicting the opening
cash price index and hence they make the ARIMA
approach inapplicable here.Neural networks are
adopted in building the forecasting model since one of
International Journal of Systems Science ISSN 0020±7721 print/ISSN 1464±5319 online
2002 Taylor & Francis Ltd
Received 15 June 2000.Revised 15 June 2001.Accepted 23 August
y Department of Business Administration,Fu-Jen Catholic
z Institute of Commerce Automation and Management,National
Taipei University of Technology,Taipei.
*To whom correspondence should be addressed.e-mail: