Forecasting Stock Market predictions using Artificial ... · Fundamental analysis involves the...
Transcript of Forecasting Stock Market predictions using Artificial ... · Fundamental analysis involves the...
International Journal of Emerging Trends in Engineering and Development Issue 6, Vol. 4 (July 2016)
Available online on http://www.rspublication.com/ijeted/ijeted_index.htm ISSN 2249-6149
©2016 RS Publication, [email protected] Page 67
Forecasting Stock Market predictions using Artificial Neural Network Models: A Survey
Dr.P.Karthikeyan*, G.Thamizhendhi**
*School of Management Studies, Kongu Engineering College, Perundurai, Erode-638052,
Tamilnadu, India. Mobile:+919843641321
** PG Department of Mathematics, Vellalar College for Women, Thindal, Erode-638012,
Tamilnadu. India.
ABSTRACT
This paper surveys recent literature in the area of Artificial Neural Networking which is
used to predict the stock market price fluctuations and return. Stock market price prediction is
one of the most recent phenomenon in the field of finance. Many models have been developed
and studies have been made by numerous researchers. Artificial Neural network (ANN) is a
technique that is widely used and perused in stock market prediction [38, 62]. This study also
seeks to explain the various models and applications of Artificial Neural Networks that predict
the stock market returns and price.
Keywords: Artificial Neural Network, Stock market predictions, Genetic Algorithm, ARIMA,
GARCH
1. INTRODUCTION
In recent years, stock markets have become more volatile. The prediction of stock price
movement is a difficult task for any financial analyst. The fundamental analysis works best for
longer period of time, whereas technical analysis is more appropriate for a shorter period. Many
researchers claim that the stock market is a chaotic system, and a non-linear deterministic system
which only appears random because of its asymmetrical fluctuations. The researchers and
academic practitioners have also projected many models using various fundamental, technical
and analytical aspects to give a more or less exact prediction on financial information
particularly stock market behaviour. Fundamental analysis involves the in-detail analysis of the
changes of the stock prices in terms of macroeconomic variables, whereas technical analysis
International Journal of Emerging Trends in Engineering and Development Issue 6, Vol. 4 (July 2016)
Available online on http://www.rspublication.com/ijeted/ijeted_index.htm ISSN 2249-6149
©2016 RS Publication, [email protected] Page 68
centers on using price, volume, and statistical charts to predict future stock movements [56].
Some traditional time series forecasting tools are also used for the prediction of stock market.
The two approaches of time series analysis and forecasting are linear approach [7], and the
nonlinear approach. The linear methods includes moving average, exponential smoothing, time
series, regression and Autoregressive integrated moving average (ARIMA) model. The
nonlinearity of the financial and stock market is propounded by many researchers and financial
analysts [1, 2]. The parametric nonlinear model includes Autoregressive Conditional
Heteroskedasticity (ARCH) [20], and General Autoregressive Conditional Heteroskedasticity
(GARCH) [6] has been in use for financial forecasting.
Many analytical models have formulated by different researchers to study the prediction of
stock price movements. The Artificial Neural Network (ANN) is the one technical tool to
forecast the stock market behavior, trends and its characteristics. A stock market is a public
market for trading the company’s shares at approved stock price. These are called Securities,
listed on stock exchanges. The price of the scripts depends upon the demand and supply gap.
Companies may issue shares to raise capital in stock market is called Primary Capital Market and
shares of respective companies listed, will allow to trade in the stock market is called secondary
capital market.
ANN is the powerful forecasting tool that predicts the stock markets. It is the non-linear
model used to map past and future value of time series data [13, 22, 37, 91]. Lapedes and
Farber [51] was studied the nonlinear time series model with artificial neural networks. The
originality of the ANN lies in their ability to determine nonlinear relationship in the input data
set without a prior assumption of the knowledge of relation between the input and the output
[26]. Artificial neural networks are applied in the fields of Computer science, Medical,
Engineering, Biology and Economic research. ANN is used for analyzing relating of economic
and financial related forecasting [10, 25, 31, 40]. Neural networks are best in discovering non-
linear relationships [9, 28, 78, 80, 87].
There are numerous studies discussed about the predictions of stock market. This paper,
focuses on various reviews in the field of ANNs used in predicting the stock market. Various
applications and models of ANN are also discussed in this paper. Avci [4]; Egeli, Ozturan,
&Badur [18] ; Karaatli, Gungor, Demir, & Kalayci [44] ; Olson & Mossman [65]; White [89]
International Journal of Emerging Trends in Engineering and Development Issue 6, Vol. 4 (July 2016)
Available online on http://www.rspublication.com/ijeted/ijeted_index.htm ISSN 2249-6149
©2016 RS Publication, [email protected] Page 69
; Leung et al., [53] have studied the stock price return based on ANN model. They examined
various prediction models based on multivariate classification techniques.
2. ARTIFICIAL NEURAL NETWORK
Artificial neural networks (ANNs) approach has been suggested as an alternative
technique to time series forecasting and it gained immense popularity in last few years.
W.S.Mculloch and W.Pitts [61] established neural network and its mathematical model,
known as McCulloch-Pitts (MP) model. This model is used for neuron’s formalization,
mathematical description and network construction. During past 70 years, the neural network
was widely used in different fields and has developed several hundred models.
The basic objective of ANNs was to construct a model for mimicking the intelligence of
human brain into machine [36, 39]. Similar to the work of a human brain, ANNs try to recognize
regularities and patterns in the input data, learn from experience and then provide generalized
results based on their known previous knowledge.
Artificial Neural Network (ANN) is a set of interconnected links that have weights
associated with them. The concept of ANN was originally arrived from biological neural
networks. All the ANN can be the deliberation of as a set of interconnected units broadly
categorized into input layer, the hidden layer and the output layer. Inputs are fed into the input
layer, and its weighted outputs are passed onto the hidden layer. The neurons in the hidden layer
(hidden neurons) are essentially concealed from view. Using additional levels of hidden neurons
provides increased flexibility and more accurate processing.
In recent periods some research works has been reported on the use of ANNs for analysis
of economy and financial markets. Stern[83] provide a introduction of ANNs as follows, the
three essential features of ANN are basic computing elements referred to as neurons, the network
architecture describing the connections between the neurons and the training algorithm used to
find values of the network parameters for performing a particular task. Each neuron performs a
simple calculation, a scalar function of a scalar input. Assuming that we make the neurons with
positive figures and designate the input to the kth
neuron as and the output from the kth
neuron
as then ok= fk(ik) where f(.) is a definite function that is characteristically done but otherwise
subjective. The neurons are connected to each other in the sense that the output from one
component can serve as part of the input to another. The weight is associated with each
construction; the weight from component j to component k is denoted as wjk. Let N(k) denote the
International Journal of Emerging Trends in Engineering and Development Issue 6, Vol. 4 (July 2016)
Available online on http://www.rspublication.com/ijeted/ijeted_index.htm ISSN 2249-6149
©2016 RS Publication, [email protected] Page 70
set of components that are connected to component k. The input to component k is then ik=
ΣjєN(k)wjkoj.
Figure 1: Single neuron with R inputs
A neuron is a processing unit that takes numerous inputs and gives a distinctive output.
The Figure 1illustrates a single neuron with R inputs each input is weighted with a
value and the output of the neuron is equal to
.
Artificial Neural Network (ANN) in the Stock Market is depicted in Figure 2. This ANN
model consists of three layers namely an input layer, a hidden layer and an output layer, every
one of which is connected to the other. At least one neuron should be engaged in each layer of
the ANN model. Inputs for the network were four different analysis (Variables/Factors) which
were represented by four neurons in the input layer. Output of the system has two patterns (0 or
1) of stock price direction. The output layer of the network consisted of only one neuron that
represents the direction of movement (Buy, Hold, and Sell of Shares). The number of neurons in
the hidden layer was determined empirically by Feed forward Artificial Neural Network (ANN)
model in order to predict Stock Market which has been illustrated in Figure.2. This model has
been developed by making some suitable modifications to the existing feed forward ANN model
[43].
w1,1
f w1,2
w1,3
w1,R
S1
S2
S3
S
R
n
b
a
International Journal of Emerging Trends in Engineering and Development Issue 6, Vol. 4 (July 2016)
Available online on http://www.rspublication.com/ijeted/ijeted_index.htm ISSN 2249-6149
©2016 RS Publication, [email protected] Page 71
Figure 2: Feed forwardArtificial Neural Network (ANN) Model to predict Stock Market.
3. VARIOUS MODELS OF NEURAL NETWORK
Various Neural network models have been discussed in this paper referring to various
existing literature in the field. The various neural network model used in time series are,
Recurrent [73, 86], Probabilistic [85, 97], Radial Basis Functions [88], Cascade Correlation [21],
General Regression Neural Net [12], Group Method of Data Handling [73], Modular ANNs [47],
Neuro Fuzzy [90]. Here we discuss some of these neural network models.
3.1. Modular Neural Network
Kimoto, Asakawa, Yoda, and Takeoka [47] have studied buying and selling time
prediction system for stocks in the Tokyo Stock Exchange based on modular neural networks.
The authors used a number of learning algorithms and prediction methods for the TOPIX (Tokyo
Stock Exchange Prices Indexes) prediction system. Further the authors applied modular neural
network model to measure the relationships among various market factors. Ramon Lawrence
[52] studied Neural Networks to Forecast Stock Market Prices. He has implemented genetic
algorithms, recurrent networks, and modular networks to predict the stock market. The Modular
neural network was used for predicting corporate bankruptcy [64]. He also discusses about
financial, as well as, political and economic data from the London Stock Exchange, and used
domain expert knowledge to select, and organise data in the modular neural network architecture
constructed for this study. The Modification and acceleration of MNN (Modular Neural
Network) operating principles was described by Schmidt and Bandar [77].
Economic Variables
GDP, Inflation, Interest rates)
Industry variables (Profitability,
Policy, Competition)
Company variables (P/E Ratio,
EPS, Book value, Dividend)
Technical Analysis (Moving average,
Oscillators, RSI, ROC)
Input Layer 1
2
n
Output Layer
Direction of
Movements
(Buy, Hold,
Sell)
Hidden Layer
International Journal of Emerging Trends in Engineering and Development Issue 6, Vol. 4 (July 2016)
Available online on http://www.rspublication.com/ijeted/ijeted_index.htm ISSN 2249-6149
©2016 RS Publication, [email protected] Page 72
3.2. ARIMA and GARCH based neural network
Jung-Hua Wang and Jia-YannLeu [41], Ahmed Ismail El-Hammady, Dr. Mohamed
Abo-Rizka [19] developed a prediction system in forecasting trend in Taiwanese stock market
and Egyptian stock market respectively based on a recurrent neural network trained by using
features extracted from ARIMA analyses. ANNs are known to provide competitive results to the
traditional time series model such as ARIMA model [13, 22, 37, 45]. The forecasting
performance of ARIMA and ANN models in forecasting Korean Stock Price Index also
compared by C. K. Lee, Y. Sehwan, and J. Jongdae [8].
Merh et al., [63] studied a comparison between hybrid approaches of ANN and ARIMA
for Indian stock trend forecasting with many instances of the ARIMA predicted values shown to
be better than those of the ANNs predicted values in relation to the actual stock value. Sterba
and Hilovska [35] argued that ARIMA model and ANN model achieved superior forecast
performance in many real-world applications.
Manish Kumar and M. Thenmozhi [50] studied the application and development of
hybrid methodology that combines both ARIMA and Artificial Neural Network Model to predict
the stock market index returns. The stock data obtained from New York Stock Exchange was
studied using ARIMA and artificial neural networks [3].
Donaldson and Kamstra [16] proposes a Neural Network modification of a GARCH
model. He used multilayer perception and density estimating neural network is used to forecast
the returns and volatility of the German Stock Index- DAX stock index. R.Glen Donaldson and
Mark Kamstra [23] constructed a semi nonparametric nonlinear GARCH model, based on the
Artificial Neural Network (ANN) literature and evaluated its ability to forecast stock return
volatility in London, New York, Tokyo and Toronto stock exchanges. The use of GARCH-
neural network model for forecasting the volatility of bid-ask spread of the Chinese stock market
[82].
Hossain, A; Nasser, M [29, 20] compare the GARCH and neural network methods in
financial time series prediction and applied GARCH model instead of
autoregressive (AR) model or autoregressive moving average (ARMA) model to compare with
Standard Back Propagation (BP) in forecasting of the four international including two Asian
stock markets indices.
International Journal of Emerging Trends in Engineering and Development Issue 6, Vol. 4 (July 2016)
Available online on http://www.rspublication.com/ijeted/ijeted_index.htm ISSN 2249-6149
©2016 RS Publication, [email protected] Page 73
Jingtao Yao, Chew Lim Tan and Hean-Lee Poh [93] developed a neural network
compared with ARIMA model that was used to predict the stock index of Kuala Lumpur Stock
Exchange, the neural network model have better returns compared with conventional ARIMA
models.
3.3. Genetic Algorithm
In financial market field, the genetic algorithms are very frequently used to discover the
best combination values of parameters in a trading rule, and they can be built into ANN models
designed to select stocks. Several studies have conducted, and these methods are proved
effective for forecasting the financial trends [42, 55]. Kim and Han [46] used neural network
tailored by Genetic Algorithm; the genetic algorithm was used to reduce the density of the
feature space. The other authors also used genetic algorithms in predicting of Stock prices
indexes [14. 59, 84] and exchange market [79]. Hassan et al., [27] projected and implemented
the fusion model by combining the HMM (Hidden Markov Model) and Genetic Algorithm to
forecast financial market behaviour. Wavelet transform to extract the short-term feature of stock
trends was used by Kishikawa and Tokinaga[48].
3.4. Recurrent Network
The finest neural networks tool for non- linear prediction is recurrent neural network
[98]. The development of RNN (Recurrent Neural Network) based on genetic learning algorithm
has a statistically significant and successful predictions [58]. A. Graves, et al., [24] introduced a
universal framework of sequence learning algorithm, evolution of recurrent systems with Linear
Outputs.
3.5.Branch Network
T. Yamashita, K. Hirasawa and Jinglu Hu [92] says that multi-branch neural networks
(MBNNs) could have higher representation and generalization ability than conventional Neural
Networks. Kotaro Hirasawa and Jinglu Hu [92] developed Multi-branch neural networks
(MBNNs) for prediction of stock prices and model were carried out in order to examine the
correctness of prediction.
3.6. Functional Link ANN
FLANN is a single layer, single neuron architecture, which has the exceptional
capability, to form complex decision regions by creating non-linear decision boundaries [12, 57].
International Journal of Emerging Trends in Engineering and Development Issue 6, Vol. 4 (July 2016)
Available online on http://www.rspublication.com/ijeted/ijeted_index.htm ISSN 2249-6149
©2016 RS Publication, [email protected] Page 74
The functional link ANN is a innovative single neuron based architecture first proposed
by Pao [70]. The original architecture of functional link artificial neural network with working
attitude of different models are provided to accomplish best forecasting and cataloging with
increase in accurateness of prediction and decrease in training time [5]. Functional link single
layer artificial neural network (FLANN) was used for long term as well as short term stock
market prediction [66].
3.7.Fuzzy Neural Network
Fuzzy theory was formulated by Zadeh [94, 95, 96] ; Zimmermann [99]. Huarng and
Yu [33] used neural networks to extract fuzzy logical relationships from fuzzy time-series to
forecast the Taiwan Stock Exchange and their model outperformed Chen’s [11] model.
Renato De C.T. and Adriano J.De O [74] presents the results of the application of Fuzzy
Neural Networks to predict the evolution of stock prices of Brazilian companies traded in the
São Paulo Stock Exchange. Pantazopoulos et al., [69] presented a neuro fuzzy approach for
predicting the prices of IBM company stock. Siekmann et al., [81] implemented a network
structure that contains the adaptable fuzzy parameters in the weights of the connections between
the first and second hidden layers. Rong-Jun Li and Zhi Bin Xiong [54] developed a fuzzy
neural network that is a set of adaptive networks and functionally equal to a fuzzy inference
system based on the comprehensive index of Shanghai stock market, designate that the
recommended fuzzy neural network could be an competent system to forecast financial
information.
3.8.Back Propagation ANN
The performance of back propagation network and regression models to predict the stock
market returns was compared [75].
Huang et al., [32] has made comparative study of application of Support Vector
Machines (SVM) and Back propagation Neural Networks (BNN) for an analysis of corporate
credit ratings. The Back Propagation algorithm designed by Rumelhart, Hinton and Williams
[76] is the best appropriate method is being intensively tested in Finance domain. Furthermore,
this method is renowned as a good algorithm for generality purposes.
4. APPLICATION OF VARIOUS ANN TO PREDICT INDIAN STOCK MARKET
Neural networks to estimate stock market actions will be a continuing area of researchers
and shareholders try hard to outstrip the market conditions. The table discusses about the existing
International Journal of Emerging Trends in Engineering and Development Issue 6, Vol. 4 (July 2016)
Available online on http://www.rspublication.com/ijeted/ijeted_index.htm ISSN 2249-6149
©2016 RS Publication, [email protected] Page 75
studies which explored on predicting Indian Stock market. The objectives, models used, data set
and major findings are depicted in Table.1.
Table 1: ANN Models used in Indian Stock Market
S.No Authors Objective Models Used
Data set
Findings
1 Manish and
Thenmozhi
[49]
To forecast India’s
S&P CNX Nifty
Index returns using
Support vector
machines (SVM)
ARIMA, Artificial
neural network,
Support vector
machines,
Daily returns on the
S&P 500 and HSI
Indices
SVM model achieves greater
forecasting accuracy and
improves prediction quality
compared to other models
experimented in the study.
2 Mayankkumar
B Patel , Sunil
R Yalamalle
[71]
To study the current
stock market trend
and collect trend
data.
Multi Layer
perceptron (MLP),
ANN
The data of
companies listed
under LIX15 index of
NSE, for the duration
of 36 months (1-1-
2011 to 1-1-2014)
have been collected.
The results from the model will
be used for comparison with the
real data to ascertain the
accuracy of the model.
3 Manna
Majumder,
MD Anwar
Hussian
[60]
Predicting the S&P
CNX Nifty 50 Index
Artificial Neural
Network, Feed
forward network,
SCP, NMSE
The trading days
from 1st January,
2000 to 31st
December, 2009
Accuracy of the performance of
the neural network is compared
using various out of sample
performance measures.
4 Panda C and
Narasimhan,
V [67]
To forecast the daily
returns of Bombay
Stock Exchange
(BSE) Sensitive
Index (Sensex)
Neural network,
random walk and
linear
autoregressive
models.
Daily BSE Sensex
Prices
Neural network out-performs
linear autoregressive and
random walk models by all
performance measures in both
in-sample and out-of-sample
forecasting of daily BSE Sensex
returns.
5 Goutam
Dutta. et al.,
[17]
Efficacy of ANN in
modelling the
Bombay Stock
Exchange
(BSE) SENSEX
ANN,
root mean square
error (RMSE) and
mean absolute
error (MAE)
Weekly closing
SENSEX values for
the two-year period
beginning January
2002.
ANN1 achieved an RMSE of
4.82 per cent and MAE of 3.93
per cent while ANN2 achieved
an RMSE of 6.87 per cent and
MAE of 5.52 per cent.
6 Pant and
Bishnoy [68]
Behaviour of daily
and weekly returns
of five Indian stock
market indices for
random walk
normality,
autocorrelation
using Qstatistic &
Dickey-Fuller test
April-1996 to June-
2001.
Indian Stock Market Indices did
not follow random walk.
7 Yusuf Perwej,
Asif Perwej
[72]
To predict the daily
excess returns of
Bombay Stock
Exchange (BSE)
indices over the
respective Treasury
bill rate returns.
Autoregressive
feed forward
Artificial Neural
Networks (ANN),
Artificial Neural
Networks model
using a Genetic
Algorithm
Bombay Stock
Exchange
Market excess returns
on a daily basis
Feasibility of the prediction task
and provides evidence that the
markets are not fluctuating
randomly and finally, to apply
the most suitable prediction
model and measure their
efficiency.
8 Jay Desai
ArtiTrivedi
Nisarg A
Joshi [15]
Computational
approach for
predicting the S&P
CNX Nifty 50 Index
Neural network
based model
Trading days from 1st
January, 2010 to 30th
November, 2011.
The model generated returns of
59.84% against buy and hold
return of -26.08%. The average
accuracy of target forecasting is
found to be 82%.
International Journal of Emerging Trends in Engineering and Development Issue 6, Vol. 4 (July 2016)
Available online on http://www.rspublication.com/ijeted/ijeted_index.htm ISSN 2249-6149
©2016 RS Publication, [email protected] Page 76
5. CONCLUSION AND FUTUREWORK
The Artificial Neural Network used in domain and it is computer based simulation model
that predicting more accurate stock price along with the movement and decision of buy or hold
or sell shares in the stock market. This paper surveyed the application of neural networks of
financial markets with particular reference to stock market prediction. This paper presents how
neural networks have been used to test the forecasting share prices.In this review of literature,
different applications of Artificial Neural Network models for predicting stock market has been
summed up. This field of research is new and emerging and there is significant enormous future
scope.
The neural network models for forecasting stock market are at a initial phase and there
are potential improvements in the prediction of accuracy and reliability of stocks. The study can
help analyst or investors to understand how the market would behave if the Stock price increases
or decreases. The future study can also focus on using macroeconomic variables to forecast the
interest rate, GDP, etc. In addition, the study should be extended to predict another kind of
financial time series like interest rate, derivative (option and future) and foreign exchange prices.
More authors put emphasis on the obligation for including more data in the models to predict the
exact share price. The researchers also emphasize the integration of neural networks with other
methods. The method of ANN is new, many possibilities for combining with other models
including linear and non-linear.
REFERENCES
1. Abhyankar, A.H., Copeland, L.S. and Wong, W. (1995) ,Non linear dynamics in real-
time equity market indices: evidence from the United Kingdom, Economic Journal,
105, 864-880.
2. Abhyankar, A.H., Copeland, L.S. and Wong, W. (1997) ,Uncovering nonlinear
structure in real time stock market indexes: the S&P 500, the DAX, the Nikkei 225,
and the FTSE 100, Journal of Business and Economic Statistics, 15, 1-14.
3. Adebiyi, A. A., Adewumi, A. O., & Ayo, C. K. (2014), Comparison of ARIMA and
Artificial Neural Networks Models for Stock Price Prediction, Journal of Applied
Mathematics, 2014.
International Journal of Emerging Trends in Engineering and Development Issue 6, Vol. 4 (July 2016)
Available online on http://www.rspublication.com/ijeted/ijeted_index.htm ISSN 2249-6149
©2016 RS Publication, [email protected] Page 77
4. Avci E. (2007) , Forecasting Daily and Sessional Returns of the Ise- 100 Index with
Neural Network Models, Dogus Universitesi Dergisi, 2(8), 128 -142.
5. Bebarta, D. K., Biswal, B., Rout, A. K., & Dash, P. K. (2012), Forecasting and
classification of Indian stocks using different polynomial functional link artificial
neural networks, In IEEE Conference, INDCON (pp. 178-182).
6. Bollerslev, T. (1986), Generalised Autoregressive Conditional Heteroskedasticity,
Journal of Econometrics, 31, 307–327.
7. Box, G. E. P. and Jenkins, G. M. (1976), Time Series Analysis: Forecasting and
Control, San Francisco: Holden-Day.
8. C. K. Lee, Y. Sehwan, and J. Jongdae (2007) “Neural network model versus
SARIMA model in forecasting Korean stock price index (KOSPI),” Issues in
Information System, vol. 8, no. 2,pp. 372–378.
9. Cameron, N., Moshiri, S. and Scuse, D. (1999) Static, dynamic and hybrid neural
networks in forecasting inflation, Computational Economics,14, 219 – 235.
10. Cheh, John J; Weinberg, Randy S; Yook, Ken C (1999). "An Application of an
Artificial Neural Network Investment System to Predict Takeover Targets", Journal
of Applied Business Research, Vol. 15 (4). p 33-45.
11. Chen, C. H. (1996). Fuzzy logic and neural network handbook. McGraw-Hill, Inc..
12. Chen, C.H(1994) "Neural networks for financial market prediction," Neural
Networks,1994. IEEE World Congress on Computational Intelligence.,1994 IEEE
International Conference on(2).
13. Chen, Y., Yang, B., Dong, J., & Abraham, A. (2005). Time-series forecasting using
flexible neural tree model. Information sciences, 174(3), 219-235.
14. Choudhry, R.; Garg, K. (2008) A Hybrid Machine Learning System for Stock Market
Forecasting, World Academy of Science, Engineering and Technology 39: 315-318.
15. Desai, J., Trivedi, A., & Joshi, N. A. (2012). Forecasting of Stock Market Indices
Using Artificial Neural Network. Shri Chimanbhai Patel Institutes, Ahmedabad
Working Paper No. CPI/MBA/2013/0003.
16. Donaldson, R. G., & Kamstra, M. (1997). An artificial neural network-GARCH
model for international stock return volatility. Journal of Empirical Finance, 4(1), 17-
46.
International Journal of Emerging Trends in Engineering and Development Issue 6, Vol. 4 (July 2016)
Available online on http://www.rspublication.com/ijeted/ijeted_index.htm ISSN 2249-6149
©2016 RS Publication, [email protected] Page 78
17. Dutta, G., Jha, P., Laha, A. K., & Mohan, N. (2006). Artificial neural network models
for forecasting stock price index in the Bombay stock exchange. Journal of Emerging
Market Finance, 5(3), 283-295.
18. Egeli, B., Ozturan, M., & Badur, B. (2003) Stock market prediction using artificial
neural networks, In Proceedings of the 3rd Hawaii international conference on
business, Honolulu, Hawaii
19. El-Hammady, A. I., & Abo-Rizka, M. (2011). Neural network based stock market
forecasting. IJCSNS, 11(8), 204.
20. Engle, R. F. (1982), Autoregressive Conditional Heteroskedasticity with Estimates of
the Variance of UK Inflation, Econometrica, 50, 987–1008.
21. Ensley,D., and Nelson,D.E (1992) "Extrapolation of Mackey-Glass data using
Cascade Correlation,"SIMULATION (58:5) p 333.
22. Giordano F, La Rocca M, Perna C (2007) Forecasting nonlinear time series with
neural network sieve bootstrap.Computational Statistics and Data Analysis,51(8):
3871–3884
23. Glen Donaldson, R., & Kamstra, M. (1999). Neural network forecast combining with
interaction effects. Journal of the Franklin Institute, 336(2), 227-236.
24. Graves, A., Fernández, S., Gomez, F., & Schmidhuber, J. (2006). Connectionist
temporal classification: labelling unsegmented sequence data with recurrent neural
networks. In Proceedings of the 23rd international conference on Machine learning
(pp. 369-376). ACM.
25. H. White (1996). Economics Prediction Using NN; The Case of IBM Daily Stock
Returns. In R.R. Trippi, E. Turban, ed., Neural Networks in Finance and Investing,
Irwin Professional Publishing, Chicago, pp. 469-481.
26. Hagan, M. T., H. B. Demuth, and M. Beale, (1996): Neural Network Design,
International Thomson Publishing Inc.
27. Hassan, M. R., Nath, B., & Kirley, M. (2007). A fusion model of HMM, ANN and
GA for stock market forecasting. Expert Systems with Applications, 33(1), 171-180.
28. Hoptroff, R.G (1993) “The Principles and Practice of Time Series Forecasting and
Business Modelling Using Neural Nets,” Neural Computing and Applications, 1, 59-
66.
International Journal of Emerging Trends in Engineering and Development Issue 6, Vol. 4 (July 2016)
Available online on http://www.rspublication.com/ijeted/ijeted_index.htm ISSN 2249-6149
©2016 RS Publication, [email protected] Page 79
29. Hossain, A., & Nasser, M. (2011). Comparison of the finite mixture of ARMA-
GARCH, back propagation neural networks and support-vector machines in
forecasting financial returns. Journal of Applied Statistics, 38(3), 533-551.
30. Hossain, A.; Nasser, M.(2008), "Comparison of GARCH and neural network methods
in financial time series prediction," Computer and Information Technology, 2008.
ICCIT 2008. 11th International Conference on , vol., no., pp.729,734, 24-27.
31. Howley, D.D., Johnson, J.D., and Raina D. (1990) Artificial Neural Systems: A New
Tool for Financial Decision-Making Financial Analysts Journal,
November/December: 63-72.
32. Huang, Z., Chen, H., Hsu, C. J., Chen, W. H., & Wu, S. (2004). Credit rating analysis
with support vector machines and neural networks: a market comparative study.
Decision support systems, 37(4), 543-558.
33. Huarng, K., & Yu, T. H. K. (2006). The application of neural networks to forecast
fuzzy time series. Physica A: Statistical Mechanics and its Applications, 363(2), 481-
491.
34. Hung, Y. C., Huang, Y. T., Ho, M. C., & Hu, C. K. (2008). Paths to globally
generalized synchronization in scale-free networks. Physical Review E, 77(1),
016202.
35. J. Sterba and K. Hilovska (2010). “The implementation of hybrid ARIMA neural
network prediction model for aggregate water consumption prediction,” Aplimat—
Journal of Applied Mathematics, vol. 3, no. 3, pp. 123–131,
36. J.M. Kihoro, R.O. Otieno, C. Wafula, “Seasonal Time Series Forecasting: A
Comparative Study of ARIMA and ANN Models”, African Journal of Science and
Technology (AJST) Science and Engineering Series Vol. 5, No. 2, pages: 41-49.
37. Jain, A. and Kumar, A.M (2007), Hybrid neural network models for hydrologic time
series forecasting, J. Applied Soft. Computing, 7(2), 2007, pp.585-592.
38. Jang Bahadur Singh, “Current Approaches in Neural Network Modeling of
Financialtime Series”, Working paper, Indian Institute of Management Bangalore.
39. Joarder Kamruzzaman, RezaulBegg, RuhulSarker, “Artificial Neural Networks in
Finance and Manufacturing”, Idea Group Publishing, USA.
International Journal of Emerging Trends in Engineering and Development Issue 6, Vol. 4 (July 2016)
Available online on http://www.rspublication.com/ijeted/ijeted_index.htm ISSN 2249-6149
©2016 RS Publication, [email protected] Page 80
40. John Cooper, (1999). "Artificial neural networks versus multivariate statistics: An
application from economics," Journal of Applied Statistics, Taylor & Francis
Journals, vol. 26(8), pages 909-921.
41. Jung-Hua Wang; Jia-Yann Leu (1996)., "Stock market trend prediction using
ARIMA-based neural networks," Neural Networks, IEEE International Conference
on , vol.4, no., pp.2160,2165 vol.4, 3-6 Jun 1996, doi: 10.1109/ICNN.1996.549236
42. Kanungo, Rama. P. (2004). Genetic Algorithms: Genesis of Stock Evaluation.
Economics WPA Working Paper, (0404007).
43. Kara, Y., Acar Boyacioglu, M., & Baykan, Ö. K. (2011). Predicting direction of stock
price index movement using artificial neural networks and support vector machines:
The sample of the Istanbul Stock Exchange. Expert systems with Applications, 38(5),
5311-5319.
44. Karaatli, M., Gungor, I., Demir, Y., & Kalayci, S. (2005) Estimating stock market
movements with neural network approach, Journal of Balikesir University, 2(1), pp.
22–48.
45. Khashei, M., & Bijari, M. (2010). An artificial neural network (p,d,q) model for
timeseries forecasting. Expert Systems with Applications, 37(1), 479-489.
46. Kim, K. J., & Han, I. (2000). Genetic algorithms approach to feature discretization in
artificial neural networks for the prediction of stock price index. Expert systems with
Applications, 19(2), 125-132.
47. Kimoto,T.,Asakawa,K.,Yoda, M., and Takeoka,M (1990)."Stock market prediction
system with modular neural networks,"Neural Networks, IJCNN International Joint
Conference ), pp 1-6.
48. Kishikawa, Y., & Tokinaga, S. (2000). Prediction of stock trends by using the
wavelet transform and the multi-stage fuzzy inference system optimized by the GA.
IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and
Computer Sciences, 83(2), 357-366.
49. Kumar, M., & Thenmozhi, M. (2007). Support vector machines approach to predict
the S&P CNX NIFTY index returns. In 10th Capital Markets Conference, Indian
Institute of Capital Markets Paper.
International Journal of Emerging Trends in Engineering and Development Issue 6, Vol. 4 (July 2016)
Available online on http://www.rspublication.com/ijeted/ijeted_index.htm ISSN 2249-6149
©2016 RS Publication, [email protected] Page 81
50. Kumar, M., & Thenmozhi, M. (2012). Causal effect of volume on stock returns and
conditional volatility in developed and emerging market. American Journal of
Finance and Accounting, 2(4), 346-362.
51. Lapedes, A. S., & Farber, R. M. (1987). Nonlinear signal processing using neural
networks: prediction and system modeling, Los Alamos Report LA-UR 87-2662.
52. Lawrence, R. (1997). Using neural networks to forecast stock market prices.
University of Manitoba.
53. Leung, M., Daouk, H. & Chen, A. (2000).Forecasting Stock Indices: A Comparison
of Classification and Level Estimation Models.International Journal of Forecasting,
16(2),173-190.
54. Li, R. J., & Xiong, Z. B. (2005). Forecasting stock market with fuzzy neural
networks. In Machine Learning and Cybernetics, 2005. Proceedings of 2005
International Conference on (Vol. 6, pp. 3475-3479). IEEE.
55. Lin, L., Cao, L., Wang, J., & Zhang, C. (2004). The applications of genetic
algorithms in stock market data mining optimisation. In Proceedings of Fifth
International Conference on Data Mining, Text Mining and their Business
Applications (pp. 273-280).
56. Louis B. Mendelsohn(2000), Trend Forecasting with Technical Analysis: Unleashing
the Hidden Power of Intermarket Analysis to Beat the Market, Marketplace Books,
Incorporated, 2000.
57. Majhi, B., Shalabi, H., & Fathi, M. (2005). FLANN based forecasting of S&P 500
index. Information Technology Journal, 4(3), 289-292.
58. Maknickienė, N., Rutkauskas, A. V., & Maknickas, A. (2011). Investigation of
financial market prediction by recurrent neural network. Innovative Technologies for
Science, Business and Education, 2(11), 3-8.
59. Mańdziuk, J., & Jaruszewicz, M. (2011). Neuro-genetic system for stock index
prediction. Journal of Intelligent and Fuzzy Systems, 22(2), 93-123.
60. Manna Majumder and MD Anwar Hussian, “Prediction of Indian stock market index
using artificial neural network"
International Journal of Emerging Trends in Engineering and Development Issue 6, Vol. 4 (July 2016)
Available online on http://www.rspublication.com/ijeted/ijeted_index.htm ISSN 2249-6149
©2016 RS Publication, [email protected] Page 82
61. McCulloch, W, and W. Pitts. (1943). A logical calculus of the ideas immanent in
nervous activity. Bulletin of Mathematical Biophysics 5:115-133. Reprinted in W. S.
McCulloch (1965/1988), Embodiments of Mind. Cambridge, MA: MIT Press.
62. Mizuno, Kosaka, Yajima and Komoda, (1998), “Application of NEURAL
NETWORK to technical analysis of stock market prediction”,Vol.7, pp. 111-120.
63. N. Merh, V. P. Saxena, and K. R. Pardasani(2010). “A comparison between hybrid
approaches of ANN and ARIMA for Indian stock trend forecasting,” Journal of
Business Intelligence, vol. 3,no. 2, pp. 23–43.
64. Nasir, M. L., John, R. I., Bennett, S. C., & Russell, D. M. (2000). Predicting
corporate bankruptcy using modular neural networks. In Computational Intelligence
for Financial Engineering, 2000.(CIFEr) Proceedings of the IEEE/IAFE/INFORMS
2000 Conference on (pp. 86-91). IEEE.
65. Olson, D.&Mossman, C. (2003). Neural Network Forecasts of Canadian Stock
Returns using Accounting Ratios.International Journal of Forecasting,19(3), 453-467.
66. Padhiary, P. K., & Mishra, A. P. (2011). Development of improved artificial neural
network model for stock market prediction. International Journal of Engineering
Science and Technology, 3(2), 1576-1581.
67. Panda, C., & Narasimhan, V. (2007). Forecasting exchange rate better with artificial
neural network. Journal of Policy Modeling, 29(2), 227-236.
68. Pant, B., & Bishnoi, T. R. (2001). Testing random walk hypothesis for Indian stock
market indices. In Research Paper Presented in UTI Capital Market Conference
Proceedings (pp. 1-15).
69. Pantazopoulos, K. N., Tsoukalas, L. H., Bourbakis, N. G., Brun, M. J., & Houstis, E.
N. (1998). Financial prediction and trading strategies using neurofuzzy approaches.
Systems, Man, and Cybernetics, Part B: Cybernetics, IEEE Transactions on, 28(4),
520-531.
70. Pao, Y. H. (1989). Adaptive pattern recognition and neural networks. Addison-
Wesley Longman Publishing Co., Inc..
71. Patel, M. B., & Yalamalle, S. R. Stock Price Prediction Using Artificial Neural
Network.
International Journal of Emerging Trends in Engineering and Development Issue 6, Vol. 4 (July 2016)
Available online on http://www.rspublication.com/ijeted/ijeted_index.htm ISSN 2249-6149
©2016 RS Publication, [email protected] Page 83
72. Perwej, Y., & Perwej, A. (2012). Prediction of the Bombay Stock Exchange (BSE)
market returns using artificial neural network and genetic algorithm.
73. Pham,D.T.,and Liu,X (1995) Neural networks for identification, prediction,and
control,Springer-Verlag, New York.
74. Raposo, Renato De CT, et al. (2005). "Using multi-agents to predict the stock market
evolution based on fundamentalist analysis and fuzzy-neural networks." Proceedings
of the 5th WSEAS International Conference on Applied Informatics and
Communications. World Scientific and Engineering Academy and Society (WSEAS).
75. Refenes, Zapranis, and Francis, (1994) Journal of Neural Networks, Stock
Performance Modeling Using Neural Networks: A Comparative Study with
Regression Models, Vol. 7, No. 2,. 375-388.
76. Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1985). Learning internal
representations by error propagation (No. ICS-8506). CALIFORNIA UNIV SAN
DIEGO LA JOLLA INST FOR COGNITIVE SCIENCE.
77. Schmidt, A. L. B. R. E. C. H. T., & Bandar, Z. U. H. A. I. R. (1998). Modularity-A
concept for new neural network architectures. In IASTED International Conference
on Computer Systems and Applications (CSA'98) (pp. 26-29).
78. Shachmurove, Y., & Witkowska, D. (2000). Utilizing artificial neural network model
to predict stock markets. University of Pennsylvania, Center for Analytic Research in
Economics and the Social Sciences.
79. Sher, G. I (2011) Evolving chart pattern sensitive neural network based forex trading
agents.2011arXiv1111.5892S
80. Shtub, Avraham; Versano, Ronen (1999). "Estimating the Cost of Steel Pipe Bending,
a Comparison between Neural Networks and Regression Analysis", International
Journal of Production Economics, Vol. 62(3). p 201-07.
81. Siekmann, S., Kruse, R., Gebhardt, J., Van Overbeek, F., & Cooke, R. (2001).
Information fusion in the context of stock index prediction. International journal of
intelligent systems, 16(11), 1285-1298.
82. Si-ming, L., Zhang-xi, L., Zhong-yi, X., & Jun-wei, M. (2012). The use of GARCH-
neural network model for forecasting the volatility of bid-ask spread of the Chinese
International Journal of Emerging Trends in Engineering and Development Issue 6, Vol. 4 (July 2016)
Available online on http://www.rspublication.com/ijeted/ijeted_index.htm ISSN 2249-6149
©2016 RS Publication, [email protected] Page 84
stock market. In Management Science and Engineering (ICMSE), 2012 International
Conference on (pp. 1899-1903). IEEE.
83. Stern,H.(1996)Neural networks in applied statistics(with
discussion).Technometrics,38,205-220.
84. Szeto, K. T.; Fong, L. Y. (2000). How Adaptive Agents in Stock Market Perform in
the Presence of Random News: A Genetic Algorithm Approach, in IDEAL'00
Proceedings of the Second International Conference on Intelligent Data Engineering
and Automated Learning, Data Mining, Financial Engineering, and Intelligent
Agents. Springer-Verlag London,UK 2000: 505-510. ISBN:3-540-41450-9.
85. Tan,H.P.,Wunsch, D.V.,and Dc,II (1995). "Conservative thirty calendar day stock
prediction using aprobabilistic neural network," Computational Intelligence for
Financial Engineering,1995.,Proceedings of the IEEElIAFE 1995),pp 113-117
86. Tenti,P."Forecasting Currency Futures Using Recurrent Neural Networks, "Proc. 3rd
International Conference.
87. Wasserman, P.D (1989).Neural Computing: Theory and Practice, Van Nostrand
Reinhold: New York.
88. Wedding,D.K.,and Cios, K.(1996). "Time series forecasting by combining RBF
networks, certainty factors, and the Box-Jenkins model, "Neurocomputing (10:2) pp
149-168.
89. White, H. (1988). Economic prediction using neural networks: The case of IBM stock
prices.Proceedings of the Second Annual IEEE Conference on Neural Networks,pp.
II:451–458. New York: IEEE Press.
90. Wong, F.S., Wang, P.Z., and Goh, T.H (1991). "Fuzzy neural systems for decision
making," Neural Networks, 1991. 1991 IEEE International Joint Conference) pp
1625-1637
91. Y. Chen, B. Yang and J. Dong (2005). ”Nonlinear System Modeling via Optimal ...
Flexible Neural Tree Model”, Information Science, 174(3-4): 219-235.
92. Yamashita, T., Hirasawa, K., & Hu, J. (2005). Application of multi-branch neural
networks to stock market prediction. In Neural Networks, 2005. IJCNN'05.
Proceedings. 2005 IEEE International Joint Conference on (Vol. 4, pp. 2544-2548).
IEEE.
International Journal of Emerging Trends in Engineering and Development Issue 6, Vol. 4 (July 2016)
Available online on http://www.rspublication.com/ijeted/ijeted_index.htm ISSN 2249-6149
©2016 RS Publication, [email protected] Page 85
93. Yao, J., Tan, C. L., & Poh, H. L. (1999). Neural networks for technical analysis: a
study on KLCI. International journal of theoretical and applied finance, 2(02), 221-
241.
94. Zadeh, L. A. (1976). A fuzzy-algorithmic approach to the definition of complex or
imprecise concepts (pp. 202-282). Birkhäuser Basel.
95. Zadeh, L.A. (1975). The Concept of Linguistic Variable and Its Application to
Approximate Reasoning I. Information Sciences, 8, 199-249
96. Zadeh, L.A., (1975). The Concept of Linguistic Variable and Its Application to
Approximate Reasoning II. Information Sciences, 8, 301-357.
97. Zaknich, A., de Silva, C.J.S., and Attikiouzel, Y.(1991) "A modified probabilistic
neural network (PNN) for nonlinear time series &nalysis,"Neural Networks,1991.
1991 IEEE International Joint Conference ) pp 1530-1535.
98. Zhang, J. S., & Xiao, X. C. (2000). Predicting chaotic time series using recurrent
neural network. Chinese Physics Letters, 17(2), 88.
99. Zimmermann H. J. (1991).Fuzzy Set Theory and Its Applications, Dordrecht, Kluver
Academic Press.