Use of Artificial Neural Network in
Stock Exchange Market
Dr. Sarsij Tripathi
Meenu Madan
Professor
IFTM, Moradabad (U.P.)
mentor.sarsij@gmail.com@gmail.com
M.Tech Scholar
IFTM, Moradabad (U.P.)
m.madan2805@gmail.com
Abstract
Data Mining is the process of finding the hidden knowledge from Data Warehouse or Data Marts. Data Mining is the part of
Knowledge Discovery in databases (KDD) process. Artificial Neural Network as a tool has proved to be beneficial in
extracting useful knowledge from the Data Warehouses which consists of large amount of data. Data Warehousing firms are
harvesting information by the process of Data Mining. The main objective of this paper is to study the use of Artificial Neural
Network (ANN) in the field of Stock Exchange Market. Artificial Neural Network is used to forecast the daily stock market
returns using different algorithms.
Recently forecasting stock market return is gaining more attention, maybe because of the fact that if the direction of the
market is successfully predicted the investors may be better guided.
Keywords – Data Mining, ANN, KDD, Data Warehouse, Data Marts, Harvesting, Forecasting, Stock Market.
1. Introduction - Data Mining is the process of finding the hidden knowledge from Data Warehouse or
Data Marts. Data mining is the process of handling information from databases which cannot be seen
directly. Therefore data mining can be used for a variety of purposes in private sector. Data analysis
techniques that have been traditionally used for such tasks include regression analysis, cluster analysis,
numerical taxonomy, multidimensional analysis, other multivariate statistical methods, stochastic models,
time series analysis and nonlinear estimation techniques [1].
Data mining takes advantage of advances in the fields of artificial intelligence (AI) and statistics .Both
disciplines have been working on problems of pattern recognition and classification [2]. The purpose of
data mining is to create decision making models for estimation of the behaviors in the future based on the
analysis of the past activities [3].
In general the data mining process iterates through five basic steps [1]:
I.
Data selection: This step consists of choosing the goal and the tools of the data mining process,
identifying the data to be mined, then choosing appropriate input attributes and output
information to represent the task.
II.
Data transformation: Transformation operations include organizing data in desired ways,
converting one type of data to another (e.g., from symbolic to numerical), defining new attributes,
reducing the dimensionality of the data, removing noise, “outliers,” normalizing, if appropriate,
deciding strategies for handling missing data.
III.
Data mining methods: The transformed data is subsequently mined, using one or more
techniques to extract patterns of interest. The user can significantly aid the data mining method by
correctly performing the proceeding steps.
IV.
Result interpretation and validation: For understanding the meaning of the synthesized
knowledge and its range of validity, the data mining application tests its robustness, using
established estimation methods and unseen data from the database. The extracted information is
also assessed (more subjectively) by comparing it with prior expertise in the application domain.
V.
Incorporation of the discovered knowledge: This consists of presenting the results to the
decision maker who may check/resolve potential conflicts with previously believed or extracted
knowledge and apply the new discovered patterns.
INCORPORATION OF THE
DISCOVERED KNOWLEDGE
RESULT INTERPRETATION AND
VALIDATION
DATA MINING METHODS
DATA TRANSFORMATION
DATA SELECTION
Fig 1: Data Mining 5 Step Process.
2. Neural Network – A neural net is the artificial representation of human brain that tries to simulate its
learning process. An artificial neural network (ANN) is often called a “Neural Network” or simply a
Neural Net (NN). Traditionally, the word Neural Network is referred to a network of biological neurons
in the nervous system that process and transmit information.
Fig 2: Biological Neuron [4]
Artificial Neural Network is an interconnected group of artificial neurons that uses a mathematical model
or computational model for information processing based on a connectionist approach to computation.
Artificial Neural Network is a network of simple processing element which can exhibit complex global
behavior, determined by the connections between the processing elements and element parameters [5].
Neural Networks (NN) are complex mathematical models that are nonlinear and input-output mapping
adaptive. NN offer uniformity of analysis and design that make them easy and efficient to use for
problems such as pattern recognition, optimization, system modeling, and data compression, among other
applications. In general NN models are composed of individual processing units called nodes. The nodes
are interconnected by links or weights. A node connection arrangement may range from full to sparse or
locally connected.
ANN generally contains multiple layers of nodes interconnected with other nodes of same or different
layers. These layers could be an input layer, hidden layer(s), or an output layer. The inputs to each layer
and the weights associated with the links are processed by a weighted summation function to produce a
sum, which is subsequently passed to an activation function and the result from there is the output for that
node. Any NN has to be calibrated, or trained, before its application.
Fig 3: Artificial Neural Network [6]
2.1. TRAINING OF NEURAL NETWORK: The training can be of three types - supervised,
unsupervised, or reinforcement type. Training is basically a procedure of adjusting the NN weights to best
represent the problem solution.
2.1.1. SUPERVISED LEARNING: Supervised learning may conceptually be thought as a teacher having
knowledge of the environment, and that knowledge is gained by a set of input-output pre-acquired data.
When the NN and the teacher are exposed to a training vector drawn from that environment, the teacher
by virtue of its prior knowledge is able to provide NN with a desired response for that vector. By desired
response is meant that the set of weights are altered, and this adjustment is carried out iteratively until the
NN emulates the teacher; the emulation is presumed to be optimum in some statistical sense using
objective criteria. This way the whole training data set is ingested and NN trained which is subsequently
ready to deal with the environment by itself. In this research the back-propagation training scheme is
employed [7].
2.1.2. UNSUPERVISED LEARNING: In the unsupervised scheme there is no external teacher to check on
the learning. Rather, provision is made for a task-independent measure of the quality of measurement that
NN has to learn, and the free parameters of the network are optimized with respect to that measure. After
the NN is tuned to the statistical regularities of the input data, it is ready for application.
2.1.3. REINFORCEMENT LEARNING: Reinforcement learning is learning what to do--how to map
situations to actions--so as to maximize a numerical reward signal. The learner is not told which actions to
take, as in most forms of machine learning, but instead must discover which actions yield the most reward
by trying them. In the most interesting and challenging cases, actions may affect not only the immediate
reward but also the next situation and, through that, all subsequent rewards. These two characteristics-trial-and-error search and delayed reward--are the two most important distinguishing features of
reinforcement learning.
Reinforcement learning is defined not by characterizing learning methods, but by characterizing a
learning problem. Any method that is well suited to solving that problem, we consider to be a
reinforcement learning method. Reinforcement learning is different from supervised learning, the kind of
learning studied in most current research in machine learning, statistical pattern recognition, and artificial
neural networks. Supervised learning is learning from examples provided by a knowledgeable external
supervisor. This is an important kind of learning, but alone it is not adequate for learning from interaction.
In interactive problems it is often impractical to obtain examples of desired behavior that are both correct
and representative of all the situations in which the agent has to act.
One of the challenges that arise in reinforcement learning and not in other kinds of learning is the tradeoff between exploration and exploitation [8].
Fig: Classification of Learning Algorithms [5]
3. APLICATION OF ANN IN STOCK MARKET EXCHANGE: Artificial Neural Network is used to
solve complex problems which people are facing in day to day life. Now-a-days Artificial Neural
Networks are used as a tool to extract relevant information from the Data Warehouses which contain a
large amount of data. Data Warehouse is the collection of subject oriented data. The major difference
between the Data Warehouse and the database is that Data Warehouse is subject oriented whereas
database is application oriented. Data mining process works on Data Warehouse or Data Marts.
ANNs have the ability of distributed information storage, parallel processing, reasoning, and selforganization. It also has the capability of rapid fitting of nonlinear data, so it can solve many problems
which are difficult for other methods. Initially, the application of the ANN in data mining was not
positive, and the main reasons were that the ANN has the defects of complex structure, poor
interpretability and long training times. But its advantages such as high affordability to the noise data with
low error rate, and the continuously advancing and optimization of various network training, pruning, and
rule extraction algorithms, make the application of the ANNs in the data mining increasingly favored by
the overwhelming majority of users.
Due to the great volume of trading in stock markets, significant profit can be made by improving trading
performance using adequate forecasting of financial variables such as stock prices, stock market indices,
and prices of financial derivatives; that is why several research works in different fields of study have
been performed on this subject so far. Atsalakis and Valavanis and Vanstone and Finnie comprehensively
surveyed these works and their involved methodologies. Among other financial variables, stock market
indices have received significant attention, and many researchers such as Atsalakis and Valavanis,
Vanstone and Finnie, and Leung et al. proposed different methodologies to forecast them [9].
Recently forecasting stock market return is gaining more attention, maybe because of the fact that if the
direction of the market is successfully predicted the investors may be better guided. The profitability of
investing and trading in the stock market to a large extent depends on the predictability. If any system be
developed which can consistently predict the trends of the dynamic stock market, would make the owner
of the system wealthy. More over the predicted trends of the market will help the regulators of the market
in making corrective measures .
Apart from these commonly used methods of prediction, some traditional time series forecasting tools are
also used for the same. In time series forecasting, the past data of the prediction variable is analyzed and
modeled to capture the patterns of the historic changes in the variable. These models are then used to
forecast the future prices. There are mainly two approaches of time series modeling and forecasting:
linear approach and the nonlinear approach. Mostly used linear methods are moving average, exponential
smoothing, time series regression etc. One of the most common and popular linear method is the
Autoregressive integrated moving average (ARIMA) model (Box and Jenkins (1976)). It presumes linear
model but is quite flexible as it can represent different types of time series, i.e. Autoregressive (AR),
moving average (MA) and combined AR and MA (ARMA) series. However, there is not much evidence
that the stock market returns are perfectly linear for the very reason that the residual variance between the
predicted return and the actual is quite high.
During last few years there has been much advancement in the application of neural network in stock
market indices forecasting with a hope that market patterns can be extracted. The novelty of the ANN lies
in their ability to discover nonlinear relationship in the input data set without a priori assumption of the
knowledge of relation between the input and the output. (Hagen et al.,1996). They independently learn the
relationship inherent in the variables. From statistical point of view neural networks are analogous to
nonparametric, nonlinear, regression model. So, neural network suits better than other models in
predicting the stock market returns [10].
The idea of stock market prediction is not new, at all. Business people often attempt to anticipate the
market by interpreting external parameters, such as economic indicators, public opinion, and current
political climate.
4. Conclusion and Future Work – Artificial Neural Network offers qualitative methods for business,
economic and medical systems that other traditional methods do not provide. In most cases Neural
Network performs better in comparison to traditional methods. With the advancement of technology the
Neural Network tools are designed with new an efficient algorithm which in turn increases its efficiency,
scalability, effectiveness to predict, classify the unseen data. So, Neural network tools are becoming
popular in field of Finance.
The motivation to implement a new technique for forecasting using soft computing and neural network
along with examination of different forecasting techniques such as Fuzzy Time Series, Data Mining
techniques and neural network is to support the development of a new system which will predict the more
accurate results. The past experiences reveal that prediction in stock market returns is a complex task.
This method will overcome limitations of traditional time series analysis techniques by adapting data
mining concepts along with fuzzy computing. Neural network easily handles the inaccuracy and any
degree of nonlinearity in the data.
References
[1] Sai Sumathi, S. N. Sivanandam , Introduction to Data Mining and its Applications, Vol. 29,
ISBN 3-540-34350-4. Verlag Berlin Heidelberg: Springer, 2006.
[2] TWO CROWS, Introduction to Data Mining and Knowledge Discovery, USA: Two Crows
Corporation, 2005.
[3] Koyuncugil, A.Serhan, Özgülbaş Nermin, “Data Mining: Data Mining: Using and Applications in
Medicine and Healthcare,” Journal of Information Technology, Vol .2, No. 2, pp.21-32, 2009.
[4] http://delphiscience.files.wordpress.com/2012/09/nb_neuron.gif
[5] RC Chakraborty, http:// www.myreaders.info/html/soft_computing.html.
[6] http://commons.wikimedia.org/wiki/File:ArtificialNeuronModel_english.png
[7] A. Weigend, N. Gershenfeld, Times Series Prediction: Forecasting the Future and
Understanding the Past, Addison-Wesley Publishing Company, ISBN 0201626020, 1994.
[8] http://webdocs.cs.ualberta.ca/~sutton/book/ebook/node7.html
[9] Niaki and Hoseinzade Journal of Industrial Engineering International 2013, 9:1 http://www.jieitsb.com/content/9/1/1 “Forecasting S&P 500 index using artificial neural networks and design of
experiments” .
[10]
Manna Majumder1 , MD Anwar Hussian2 “FORECASTING OF INDIAN STOCK
MARKET INDEX USING ARTIFICIAL NEURAL NETWORK”.