\documentclass[11pt,twoside]{article}\makeatletter \IfFileExists{xcolor.sty}% {\RequirePackage{xcolor}}% {\RequirePackage{color}} \usepackage{colortbl} \usepackage{wrapfig} \usepackage{ifxetex} \ifxetex \usepackage{fontspec} \usepackage{xunicode} \catcode`⃥=\active \def⃥{\textbackslash} \catcode`❴=\active \def❴{\{} \catcode`❵=\active \def❵{\}} \def\textJapanese{\fontspec{Noto Sans CJK JP}} \def\textChinese{\fontspec{Noto Sans CJK SC}} \def\textKorean{\fontspec{Noto Sans CJK KR}} \setmonofont{DejaVu Sans Mono} \else \IfFileExists{utf8x.def}% {\usepackage[utf8x]{inputenc} \PrerenderUnicode{–} }% {\usepackage[utf8]{inputenc}} \usepackage[english]{babel} \usepackage[T1]{fontenc} \usepackage{float} \usepackage[]{ucs} \uc@dclc{8421}{default}{\textbackslash } \uc@dclc{10100}{default}{\{} \uc@dclc{10101}{default}{\}} \uc@dclc{8491}{default}{\AA{}} \uc@dclc{8239}{default}{\,} \uc@dclc{20154}{default}{ } \uc@dclc{10148}{default}{>} \def\textschwa{\rotatebox{-90}{e}} \def\textJapanese{} \def\textChinese{} \IfFileExists{tipa.sty}{\usepackage{tipa}}{} \fi \def\exampleFont{\ttfamily\small} \DeclareTextSymbol{\textpi}{OML}{25} \usepackage{relsize} \RequirePackage{array} \def\@testpach{\@chclass \ifnum \@lastchclass=6 \@ne \@chnum \@ne \else \ifnum \@lastchclass=7 5 \else \ifnum \@lastchclass=8 \tw@ \else \ifnum \@lastchclass=9 \thr@@ \else \z@ \ifnum \@lastchclass = 10 \else \edef\@nextchar{\expandafter\string\@nextchar}% \@chnum \if \@nextchar c\z@ \else \if \@nextchar l\@ne \else \if \@nextchar r\tw@ \else \z@ \@chclass \if\@nextchar |\@ne \else \if \@nextchar !6 \else \if \@nextchar @7 \else \if \@nextchar (8 \else \if \@nextchar )9 \else 10 \@chnum \if \@nextchar m\thr@@\else \if \@nextchar p4 \else \if \@nextchar b5 \else \z@ \@chclass \z@ \@preamerr \z@ \fi \fi \fi \fi \fi \fi \fi \fi \fi \fi \fi \fi \fi \fi \fi \fi} \gdef\arraybackslash{\let\\=\@arraycr} \def\@textsubscript#1{{\m@th\ensuremath{_{\mbox{\fontsize\sf@size\z@#1}}}}} \def\Panel#1#2#3#4{\multicolumn{#3}{){\columncolor{#2}}#4}{#1}} \def\abbr{} \def\corr{} \def\expan{} \def\gap{} \def\orig{} \def\reg{} \def\ref{} \def\sic{} \def\persName{}\def\name{} \def\placeName{} \def\orgName{} \def\textcal#1{{\fontspec{Lucida Calligraphy}#1}} \def\textgothic#1{{\fontspec{Lucida Blackletter}#1}} \def\textlarge#1{{\large #1}} \def\textoverbar#1{\ensuremath{\overline{#1}}} \def\textquoted#1{‘#1’} \def\textsmall#1{{\small #1}} \def\textsubscript#1{\@textsubscript{\selectfont#1}} \def\textxi{\ensuremath{\xi}} \def\titlem{\itshape} \newenvironment{biblfree}{}{\ifvmode\par\fi } \newenvironment{bibl}{}{} \newenvironment{byline}{\vskip6pt\itshape\fontsize{16pt}{18pt}\selectfont}{\par } \newenvironment{citbibl}{}{\ifvmode\par\fi } \newenvironment{docAuthor}{\ifvmode\vskip4pt\fontsize{16pt}{18pt}\selectfont\fi\itshape}{\ifvmode\par\fi } \newenvironment{docDate}{}{\ifvmode\par\fi } \newenvironment{docImprint}{\vskip 6pt}{\ifvmode\par\fi } \newenvironment{docTitle}{\vskip6pt\bfseries\fontsize{22pt}{25pt}\selectfont}{\par } \newenvironment{msHead}{\vskip 6pt}{\par} \newenvironment{msItem}{\vskip 6pt}{\par} \newenvironment{rubric}{}{} \newenvironment{titlePart}{}{\par } \newcolumntype{L}[1]{){\raggedright\arraybackslash}p{#1}} \newcolumntype{C}[1]{){\centering\arraybackslash}p{#1}} \newcolumntype{R}[1]{){\raggedleft\arraybackslash}p{#1}} \newcolumntype{P}[1]{){\arraybackslash}p{#1}} \newcolumntype{B}[1]{){\arraybackslash}b{#1}} \newcolumntype{M}[1]{){\arraybackslash}m{#1}} \definecolor{label}{gray}{0.75} \def\unusedattribute#1{\sout{\textcolor{label}{#1}}} \DeclareRobustCommand*{\xref}{\hyper@normalise\xref@} \def\xref@#1#2{\hyper@linkurl{#2}{#1}} \begingroup \catcode`\_=\active \gdef_#1{\ensuremath{\sb{\mathrm{#1}}}} \endgroup \mathcode`\_=\string"8000 \catcode`\_=12\relax \usepackage[a4paper,twoside,lmargin=1in,rmargin=1in,tmargin=1in,bmargin=1in,marginparwidth=0.75in]{geometry} \usepackage{framed} \definecolor{shadecolor}{gray}{0.95} \usepackage{longtable} \usepackage[normalem]{ulem} \usepackage{fancyvrb} \usepackage{fancyhdr} \usepackage{graphicx} \usepackage{marginnote} \renewcommand{\@cite}[1]{#1} \renewcommand*{\marginfont}{\itshape\footnotesize} \def\Gin@extensions{.pdf,.png,.jpg,.mps,.tif} \pagestyle{fancy} \usepackage[pdftitle={Performance Analysis of Stock Price Prediction using Artificial Neural Network}, pdfauthor={}]{hyperref} \hyperbaseurl{} \paperwidth210mm \paperheight297mm \def\@pnumwidth{1.55em} \def\@tocrmarg {2.55em} \def\@dotsep{4.5} \setcounter{tocdepth}{3} \clubpenalty=8000 \emergencystretch 3em \hbadness=4000 \hyphenpenalty=400 \pretolerance=750 \tolerance=2000 \vbadness=4000 \widowpenalty=10000 \renewcommand\section{\@startsection {section}{1}{\z@}% {-1.75ex \@plus -0.5ex \@minus -.2ex}% {0.5ex \@plus .2ex}% {\reset@font\Large\bfseries}} \renewcommand\subsection{\@startsection{subsection}{2}{\z@}% {-1.75ex\@plus -0.5ex \@minus- .2ex}% {0.5ex \@plus .2ex}% {\reset@font\Large}} \renewcommand\subsubsection{\@startsection{subsubsection}{3}{\z@}% {-1.5ex\@plus -0.35ex \@minus -.2ex}% {0.5ex \@plus .2ex}% {\reset@font\large}} \renewcommand\paragraph{\@startsection{paragraph}{4}{\z@}% {-1ex \@plus-0.35ex \@minus -0.2ex}% {0.5ex \@plus .2ex}% {\reset@font\normalsize}} \renewcommand\subparagraph{\@startsection{subparagraph}{5}{\parindent}% {1.5ex \@plus1ex \@minus .2ex}% {-1em}% {\reset@font\normalsize\bfseries}} \def\l@section#1#2{\addpenalty{\@secpenalty} \addvspace{1.0em plus 1pt} \@tempdima 1.5em \begingroup \parindent \z@ \rightskip \@pnumwidth \parfillskip -\@pnumwidth \bfseries \leavevmode #1\hfil \hbox to\@pnumwidth{\hss #2}\par \endgroup} \def\l@subsection{\@dottedtocline{2}{1.5em}{2.3em}} \def\l@subsubsection{\@dottedtocline{3}{3.8em}{3.2em}} \def\l@paragraph{\@dottedtocline{4}{7.0em}{4.1em}} \def\l@subparagraph{\@dottedtocline{5}{10em}{5em}} \@ifundefined{c@section}{\newcounter{section}}{} \@ifundefined{c@chapter}{\newcounter{chapter}}{} \newif\if@mainmatter \@mainmattertrue \def\chaptername{Chapter} \def\frontmatter{% \pagenumbering{roman} \def\thechapter{\@roman\c@chapter} \def\theHchapter{\roman{chapter}} \def\thesection{\@roman\c@section} \def\theHsection{\roman{section}} \def\@chapapp{}% } \def\mainmatter{% \cleardoublepage \def\thechapter{\@arabic\c@chapter} \setcounter{chapter}{0} \setcounter{section}{0} \pagenumbering{arabic} \setcounter{secnumdepth}{6} \def\@chapapp{\chaptername}% \def\theHchapter{\arabic{chapter}} \def\thesection{\@arabic\c@section} \def\theHsection{\arabic{section}} } \def\backmatter{% \cleardoublepage \setcounter{chapter}{0} \setcounter{section}{0} \setcounter{secnumdepth}{2} \def\@chapapp{\appendixname}% \def\thechapter{\@Alph\c@chapter} \def\theHchapter{\Alph{chapter}} \appendix } \newenvironment{bibitemlist}[1]{% \list{\@biblabel{\@arabic\c@enumiv}}% {\settowidth\labelwidth{\@biblabel{#1}}% \leftmargin\labelwidth \advance\leftmargin\labelsep \@openbib@code \usecounter{enumiv}% \let\p@enumiv\@empty \renewcommand\theenumiv{\@arabic\c@enumiv}% }% \sloppy \clubpenalty4000 \@clubpenalty \clubpenalty \widowpenalty4000% \sfcode`\.\@m}% {\def\@noitemerr {\@latex@warning{Empty `bibitemlist' environment}}% \endlist} \def\tableofcontents{\section*{\contentsname}\@starttoc{toc}} \parskip0pt \parindent1em \def\Panel#1#2#3#4{\multicolumn{#3}{){\columncolor{#2}}#4}{#1}} \newenvironment{reflist}{% \begin{raggedright}\begin{list}{} {% \setlength{\topsep}{0pt}% \setlength{\rightmargin}{0.25in}% \setlength{\itemsep}{0pt}% \setlength{\itemindent}{0pt}% \setlength{\parskip}{0pt}% \setlength{\parsep}{2pt}% \def\makelabel##1{\itshape ##1}}% } {\end{list}\end{raggedright}} \newenvironment{sansreflist}{% \begin{raggedright}\begin{list}{} {% \setlength{\topsep}{0pt}% \setlength{\rightmargin}{0.25in}% \setlength{\itemindent}{0pt}% \setlength{\parskip}{0pt}% \setlength{\itemsep}{0pt}% \setlength{\parsep}{2pt}% \def\makelabel##1{\upshape ##1}}% } {\end{list}\end{raggedright}} \newenvironment{specHead}[2]% {\vspace{20pt}\hrule\vspace{10pt}% \phantomsection\label{#1}\markright{#2}% \pdfbookmark[2]{#2}{#1}% \hspace{-0.75in}{\bfseries\fontsize{16pt}{18pt}\selectfont#2}% }{} \def\TheFullDate{2012-01 2012-05-15 (revised: January 2012 15 May 2012)} \def\TheID{\makeatother } \def\TheDate{2012-01 2012-05-15} \title{Performance Analysis of Stock Price Prediction using Artificial Neural Network} \author{}\makeatletter \makeatletter \newcommand*{\cleartoleftpage}{% \clearpage \if@twoside \ifodd\c@page \hbox{}\newpage \if@twocolumn \hbox{}\newpage \fi \fi \fi } \makeatother \makeatletter \thispagestyle{empty} \markright{\@title}\markboth{\@title}{\@author} \renewcommand\small{\@setfontsize\small{9pt}{11pt}\abovedisplayskip 8.5\p@ plus3\p@ minus4\p@ \belowdisplayskip \abovedisplayskip \abovedisplayshortskip \z@ plus2\p@ \belowdisplayshortskip 4\p@ plus2\p@ minus2\p@ \def\@listi{\leftmargin\leftmargini \topsep 2\p@ plus1\p@ minus1\p@ \parsep 2\p@ plus\p@ minus\p@ \itemsep 1pt} } \makeatother \fvset{frame=single,numberblanklines=false,xleftmargin=5mm,xrightmargin=5mm} \fancyhf{} \setlength{\headheight}{14pt} \fancyhead[LE]{\bfseries\leftmark} \fancyhead[RO]{\bfseries\rightmark} \fancyfoot[RO]{} \fancyfoot[CO]{\thepage} \fancyfoot[LO]{\TheID} \fancyfoot[LE]{} \fancyfoot[CE]{\thepage} \fancyfoot[RE]{\TheID} \hypersetup{citebordercolor=0.75 0.75 0.75,linkbordercolor=0.75 0.75 0.75,urlbordercolor=0.75 0.75 0.75,bookmarksnumbered=true} \fancypagestyle{plain}{\fancyhead{}\renewcommand{\headrulewidth}{0pt}} \date{} \usepackage{authblk} \providecommand{\keywords}[1] { \footnotesize \textbf{\textit{Index terms---}} #1 } \usepackage{graphicx,xcolor} \definecolor{GJBlue}{HTML}{273B81} \definecolor{GJLightBlue}{HTML}{0A9DD9} \definecolor{GJMediumGrey}{HTML}{6D6E70} \definecolor{GJLightGrey}{HTML}{929497} \renewenvironment{abstract}{% \setlength{\parindent}{0pt}\raggedright \textcolor{GJMediumGrey}{\rule{\textwidth}{2pt}} \vskip16pt \textcolor{GJBlue}{\large\bfseries\abstractname\space} }{% \vskip8pt \textcolor{GJMediumGrey}{\rule{\textwidth}{2pt}} \vskip16pt } \usepackage[absolute,overlay]{textpos} \makeatother \usepackage{lineno} \linenumbers \begin{document} \author[1]{Dr. K.K.Sureshkumar} \author[2]{ Dr.N.M.Elango} \affil[1]{ Kongu Arts and Science College / Bharathiar University} \renewcommand\Authands{ and } \date{\small \em Received: 5 April 2012 Accepted: 30 April 2012 Published: 15 May 2012} \maketitle \begin{abstract} Stock market predictions are one of the challenging tasks for financial investors across the globe. This challenge is due to the uncertainty and volatility of the stock prices in the market. Due to technology and globalization of business and financial markets it is important to predict the stock prices more quickly and accurately. Last few years there has been much improvement in the field of Neural Network (NN) applications in business and financial markets. Artificial Neural Network (ANN) methods are mostly implemented and play a vital role in decision making for stock market predictions. Multi Layer Perceptron (MLP) architecture with back propagation algorithm has the ability to predict with greater accuracy than other neural network algorithms. In this research, neural works predict tools are used to predict the future stock prices and their performance statistics will be evaluated. This would help the investor to analyze better in business decisions such as buy or sell a stock. \end{abstract} \keywords{Artificial Neural Network (ANN), Multi Layer Perceptron (MLP), National Stock Exchange (NSE), Stock Prediction, Performance Measures.} \begin{textblock*}{18cm}(1cm,1cm) % {block width} (coords) \textcolor{GJBlue}{\LARGE Global Journals \LaTeX\ JournalKaleidoscope\texttrademark} \end{textblock*} \begin{textblock*}{18cm}(1.4cm,1.5cm) % {block width} (coords) \textcolor{GJBlue}{\footnotesize \\ Artificial Intelligence formulated this projection for compatibility purposes from the original article published at Global Journals. However, this technology is currently in beta. \emph{Therefore, kindly ignore odd layouts, missed formulae, text, tables, or figures.}} \end{textblock*} \let\tabcellsep& \section[{INTRODUCTION}]{INTRODUCTION}\par tock price prediction is a heated topic in prediction study of financial area. The use of ANN in business environments has been increasing over the last few years. Excellent algorithm has been applied to predict stock price or index. Interest in neural networks has led to a considerable surge in research activities in the past decade. Artificial neural network models are based on the neural structure of the brain. The brain learns from experience and so do artificial neural networks. As a useful analytical tool, ANN is widely applied in analyzing the business data stored in database or data warehouse. Identifying customer behavior patterns and predicting stock price are emerging areas of neural network research and its application. Most of the companies have created new methods of evaluating financial data and investment decisions. Artificial Neural Networks are being used by most companies for improved forecasting capabilities in analysis of stock market. So, artificial neural network suits better than other models in predicting the stock market.\par To predict stock prices there are so many conventional techniques can be used, in which fundamental and technical analysis one among them (Atiya, A. F, El-Shoura et al, 1999). Fundamental analysis involves various macro-economic factors, results of the company, financial conditions and other related attributes are used to measure the value of the company with reflect to stock price changes. Technical analysis, on the other hand, involves analyzing statistics generated by market activity, such as past prices and volume (Kai Keng Ang and Chai Quek, 2006). Recent development in soft computing has set a new dimension in the field of financial forecasting. Tools based on ANN have gained more popularity due to their inherent capabilities to approximate any non linear function to a high degree of accuracy.\par The idea of forecasting using neural network is to find an approximation of mapping between the input and output data through training. The trained neural network is then used to predict the values for the future \hyperref[b0]{(Abhyankar, A. et al, 1997)}. This research work presents the use of artificial neural network as a forecasting tool for predicting the stock market price.\par The remainder of the paper is organized as follows. Section II reviews the background study of the stock market prediction by Artificial Neural Network. Section III focuses on the objectives of the study. Section IV discusses about the basic of Artificial Neural Network; benefits and limitations of ANN were presented. Section V discusses about the Indian Stock market. Section VI explains about data and methodology of using NeuralWorks Predict to predict the stock prices and calculating result performance. Section VII concludes the research. \section[{II.}]{II.} \section[{BACKGROUND STUDY}]{BACKGROUND STUDY}\par In the last two decades lot of research has been done on models based on intelligent soft computing. In general, the approaches to predict stock market could be classified into two classes, fundamental analysis and technical analysis (Kai Keng Ang and Chai Quek, 2006). Fundamental analysis is based on macroeconomic data and the basic financial status of companies like money supply, interest rate, inflationary rates, dividend yields, earnings yield, cash flow yield, book to market ratio, price-earnings ratio, lagged returns {\ref (Fama and French, 1988;}\hyperref[b18]{Lakonishok, 1994)}. Technical analysis is based on the rationale that history will repeat itself and that and hidden in past trading activities and by analyzing patterns and trends shown in price and volume charts \hyperref[b31]{(Smirlock and Starks, 1985;}\hyperref[b5]{Brush 1986}).\par According to (Refenes, Zapranis and Franchis, 1994) "neural networks are capable of making better prediction in capturing the structural relationship between a stock's performance and its determinant factors more accurately than MLR models". \hyperref[b17]{(Kryzanowski, Galler and Wright, 1993)} using Boltzmann machine trained an artificial neural network with 149 test cases of positive (rise in the stock price) and negative (fall in the stock price) returns for the years 1987-1989 and compared this to training the network with positive, neutral (unchanged stock price), and negative returns for the same 149 test cases for the years 1987-1989. The network predicted 72\% correct results with positive and negative returns. However the network predicted only 46\% correct results with positive, neutral, and negative returns.\par Using neural networks to predict financial markets has been an active research area in both fundamental and technical analysis, since the late 1980s \hyperref[b38]{(White, 1988} Fujitsu a Japanese technology company and Nikko Securities -an investment company joined together to develop a stock market prediction system for TOPIX (Tokyo based stock index). The emergence of artificial intelligence techniques has seen their enormous application to financial forecasting, such as expert systems (Tsaih Yenshan Hsu, and Charles Lai, 1998), fuzzy logic \hyperref[b12]{(Hiemstra, 1994)}, and neural networks \hyperref[b17]{(Kryzanowski, Galler and Wright, 1993)}. Among them, neural networks are the most popular and successful tools. There is extensive literature about the application of neural networks in financial forecasting \hyperref[b2]{(Azoff, 1994;}\hyperref[b11]{Goonatilake and Treleaven, 1995;}\hyperref[b40]{Wong and Selvi, 1998)}. One of the most popular Journals published on the application of neural networks in finance is the Journal of Computational Intelligence in Finance \hyperref[b4]{(Bhagirathi Nayak, et al, 2011)}.\par Also, all of the researches using neural network applications in prediction of stock market trend are mainly based on the assumption that the basic laws in a certain stock market is consistent through the time of experiment data. \section[{III.}]{III.} \section[{OBJECTIVES OF THE STUDY}]{OBJECTIVES OF THE STUDY}\par The main objective of this study is to use NeuralWorks Predict tool to obtain more accurate stock prediction price and to evaluate them with some performance measures. This study can be used to reduce the error proportion in predicting the future stock prices. It increases the chances for the investors to predict the prices more accurately by reducing error percentage and thus gain benefits in share markets.\par IV. \section[{ARTIFICIAL NEURAL NETWORK}]{ARTIFICIAL NEURAL NETWORK}\par Artificial Neural Network (ANN) is an information processing system where the elements called neurons, process the information. The signals are transmitted by means of connection links. The links possess an associated weight, which is multiplied along with the incoming signal (net input) for any typical neural network. The output signal is obtained by applying activations to the net input. The network consists of a set of sensory units that constitute the input layer and one or more hidden layer of computation modes. The input signal passes through the network in the forward direction. This type of network is called as multilayer perceptron (MLP) (Sivanandam, S.N. et al, 2006). The multilayer perceptron are used with supervised learning and have to lead the successful back propagation algorithm where logistic sigmoid function is widely used.\par The MLP network has hidden neurons and this will make the network more active for complex tasks. The layers of network are connected by synaptic weights and have a high computational efficiency. \section[{a) Benefits of Using Artificial Neural Network}]{a) Benefits of Using Artificial Neural Network}\par Neural networks often lead to significant results, e.g. in weather forecasting, a rule of weather change is less probable than a steady weather pattern. According to \hyperref[b28]{(Schoneburg, 1990)}, this is also true for stock prices.\par A key aspect to successful forecasting lies in the ability to merge data available in diverse formats \hyperref[b32]{(Steven H. Kim and Se Hak Chun, 1998)}. The data analysis performed by neural networks tolerates a considerable amount of imprecise and incomplete input data due to the distributed mode of information processing. Neural network lie in their ability to predict accurately even in situations with uncertain data, and the possible combinations with other methods. Despite the benefits of artificial neural networks, there are still some limitations to neural networks that are discussed below. \section[{b) Limitations of Artificial Neural Network}]{b) Limitations of Artificial Neural Network}\par Some methods are executed with insufficient reliability tests, data design and with inability to identify the optimal topology for a specific problem domain.\par There is no known method of designing an optimal neural network, but the best network is highly dependent on the data and application (Carlos Cinca. 1996). Some of the limitations are mentioned below: 1. NN require very large number of previous data. 2. The best NN architecture topology is still unknown. 3. For complex networks the result and accuracy may decrease. 4. Statistical relevance of the result is needed. 5. More careful data design is needed and systematically analyzed.\par In order to improve the NN applications, there are some other limitations, concerning the problems of evaluation and implementation of NN that should be discussed. Large number of research is done and implemented by companies that are not published in scientific indexes.\par V. \section[{INDIAN STOCK MARKET}]{INDIAN STOCK MARKET}\par Investors are mostly preferred the stock market investments because it has the opportunity of highest return over other schemes. For companies, stock market is one of the key sources to raise money through initial public offer (IPO). This allows businesses to be publicly traded, or raise additional capital for expansion by selling shares of ownership of the company in a public market. Indian stock market is mainly consists of two major stock indices, Bombay Stock Exchange (BSE) and National Stock Exchange (NSE). The benchmark for these two exchanges are Sensex (30 Stocks) and Nifty (50 Stocks).\par BSE was the first stock exchange in the country and approved under the Securities Contract Regulation Act, 1956. Sensex is an index of 30 stocks with 12 major sectors. In the year 1993, National Stock Exchange of India has been the frontier of Indian securities market. NSE is located at Mumbai, India referred as Nifty. Nifty is a well diversified index consisting of 50 major stocks from 21 sectors of the economy (Refer NSE, 2010). It is the largest stock exchange in India in terms of daily turnover and number of trades, for both equities and derivative trading. Trading on both exchanges is carried out in dematerialized form.\par Securities and Exchange Board of India (SEBI) is the regulatory authority and have the rights to monitor all the stock markets in India established by Government of India in the year 1988. The main goal of the board is to protect the investors in securities and regulate the stock market. There are 23 stock exchanges in India, out of that only 18 stock exchanges are currently in the operative mode. Among 18 exchanges BSE and NSE are considered to be the primary exchanges of India.\par VI. \section[{DATA AND METHODOLOGY}]{DATA AND METHODOLOGY}\par The actual problem discussed in this paper is to forecast the stock price of National Stock Exchange in India. For this purpose we have used available daily stock data of TCS (i.e., bhavcopy) from the National Stock Exchange beginning from 01-November-2009 to 12-December-2011 (Refer NSE, 2011).\par For this study, we select 508 day's NSE stock data of TCS Company. The data field used in this research consists of previous close, open price, high price, low price and close price. In order to predict the stock price, past data is necessary and it has been collected for the trading days from 01-November-2009 to 12-December-2011. The historical data set is available on the National Stock Exchange website.\par The main task is to predict the stock price of TCS will be up or down for tomorrow by using the historical values of the company stock. In this research, NeuralWorks Predict version 3.24 packages are applied to predict the future stock price of TCS The historic data of previous close, open price, high price, low price and closing price data is used. NeuralWorks Predict 3.24 tool is used throughout the process, this research choose 5 important attributes including previous close, open price, high price, low price and closing price. The performance of the neural network largely depends on the architecture of the neural network. Issues critical to the neural network modeling like selection of input variables, data pre-processing technique, network architecture design and performance measuring statistics should be considered carefully. The close correlation between the market value predicted by the neural network and the true value suggests that such networks may indeed become very powerful tools in financial applications. In this study, a real world output range is calculated whose limits are the minimum and maximum of all real world targets and real world model outputs. This range is used in several of the analysis results as shown in the Table {\ref 2}. \section[{Table.2 : Results Interpretation and Performance}]{Table.2 : Results Interpretation and Performance} \section[{Statistics c) Output Summary}]{Statistics c) Output Summary}\par The result of the predicted value has been shown in the Fig. {\ref 1}. In Fig. {\ref 1}, the actual close price of TCS have compared with the predicted price. Here, days refer to 508 values for each day starting from (19-November-2008 to 14-December-2010). \section[{Fig.1 : Comparison of Actual Vs Predicted Price}]{Fig.1 : Comparison of Actual Vs Predicted Price}\par The error percentage rate of the actual close price and predicted price of TCS as shown in Fig. {\ref 2}. \section[{Fig.2 : Error Percentage rate of Actual Close Price Vs Predicted Price}]{Fig.2 : Error Percentage rate of Actual Close Price Vs Predicted Price}\par There are many different methods to measure performance of systems. In order to evaluate the net performance of the stock value some of the following indicators have to be considered.\par The indicators are R, Net-R, Average Absolute, RMS, Accuracy measures and Confidence limits. Net-R measure is the linear correlation between the real world target output and the raw neural net output. RMSE is a basic measure is used to find out the difference between values predicted by a model and the value actually observed.\par We have used NeuralWorks Predict package tool for training, testing and predicting the stock prices. It is found that the percentage of correct prediction has been made and the result of this analysis is shown in the Table {\ref 2}.\par The train and test data sets are selected from the primary and secondary working sets, which will preliminary, trim the data sets. The following are the outcomes of all test and train set data. \begin{figure}[htbp] \noindent\textbf{}\includegraphics[]{image-2.png} \caption{\label{fig_0}}\end{figure} \begin{figure}[htbp] \noindent\textbf{}\includegraphics[]{image-3.png} \caption{\label{fig_1}Performance}\end{figure} \begin{figure}[htbp] \noindent\textbf{4}\includegraphics[]{image-4.png} \caption{\label{fig_2}Fig. 4 :}\end{figure} \begin{figure}[htbp] \noindent\textbf{5}\includegraphics[]{image-5.png} \caption{\label{fig_3}Fig. 5 :}\end{figure} \begin{figure}[htbp] \noindent\textbf{.} \par \begin{longtable}{} \end{longtable} \par \caption{\label{tab_1}Table . 3}\end{figure} \footnote{© 2012 Global Journals Inc. (US) Global Journal of Computer Science and Technology Volume XII Issue I Version I} \footnote{© 2012 Global Journals Inc. (US)} \footnote{January 2012 © 2012 Global Journals Inc. (US) VIII.} \backmatter \subsection[{CONCLUSION}]{CONCLUSION}\par In this research, we examined and applied multilayer perceptron model by using the NeuralWorks Predict tool. The results from analysis shows that NeuralWorks Predict offer the ability to predict the stock prices more accurately than the other existing tools and techniques. The accuracy of the predicted output values that within 20\% of their corresponding target output value. By using this tool one can have the ability to forecast the stock price of NSE more accurately. This analysis can be used to reduce the error percentage in predicting the future stock prices. It increases the chances for the investors to predict the prices more accurately by reducing the error percentage and hence increase their profit in share markets. Utilizing neural network models together with other forecasting tools and techniques can be considered yet another valuable advancement in the age of technology. \begin{bibitemlist}{1} \bibitem[Page]{b13}\label{b13} \textit{}, Page . p. . \bibitem[Atiya et al. ()]{b1}\label{b1} ‘A comparison between neural network forecasting techniques case study: river flow forecasting’. A F Atiya , S M El-Shoura , S Shaheen , M S El-Sherif . \textit{IEEE Transaction Neural Networks}, 1999. p. . \bibitem[Murphy ()]{b19}\label{b19} ‘A Comprehensive Guide to Trading Methods and Applications’. J Murphy . \textit{Technical Analysis of the Financial Markets}, 1999. Prentice Hall Press. \bibitem[Smirlock and Starks ()]{b31}\label{b31} ‘A Further Examination of Stock Price Changes and Transaction Volume’. M Smirlock , Laura Starks . \textit{Journal of Financial Research} 1985. 8 p. . \bibitem[Swales and Yoon ()]{b33}\label{b33} ‘Applying artificial neural networks to investment analysis’. G S Swales , Y Yoon . \textit{Financial Analysts Journal} 1992. 48 (5) . \bibitem[Rogers and Vemuri ()]{b26}\label{b26} \textit{Artificial Neural Networks Forecasting Time Series}, R Rogers , V Vemuri . 1994. Los Alamitos, CA: IEEE Computer Society Press. \bibitem[Azoff ()]{b2}\label{b2} E M Azoff . \textit{Neural Network Time Series Forecasting of Financial Markets}, (New York) 1994. Wiley. \bibitem[Conference on Statistics and Related Fields (2009)]{b22}\label{b22} \textit{Conference on Statistics and Related Fields}, (Hawaii, USA) June 5-9. \bibitem[Lakonishok et al. ()]{b18}\label{b18} ‘Contrarian investment, extrapolation, and risk’. Josef Lakonishok , Andrei Shleifer , Robert Vishny . \textit{Journal of Finance} 1994. 49 p. . \bibitem[Katz ()]{b15}\label{b15} ‘Developing neural network forecasters for trading’. J O Katz . \textit{Technical Analysis of Stocks and Commodities} 1992. 10 (4) . \bibitem[Fama and French ()]{b8}\label{b8} ‘Dividend Yields and Expected Stock returns’. E F Fama , K R French . \textit{Journal of Financial Economics} 1988b. 22 p. . \bibitem[White ()]{b38}\label{b38} ‘Economic predictions using neural networks: the case of IBM daily stock returns’. H White . \textit{Proceedings of IEEE International Conference on Neural Networks}, (IEEE International Conference on Neural Networks) 1988. 2 p. . \bibitem[Brush ()]{b5}\label{b5} ‘Eight Relative Strength Models Compared’. J Brush . \textit{Journal of Portfolio Management} 1986. p. . \bibitem[Bhagirathi Nayak et al. ()]{b4}\label{b4} ‘Forecasting of Financial Markets -Application of Fuzzy Association Rules’. Bhagirathi Nayak , . C Dr , Nahak , Dr , K R Arun , Misra . \textit{International Journal of Research in Commerce IT \& Management} 2231- 5756. 2011. (1) . \bibitem[Tsaih et al. ()]{b34}\label{b34} ‘Forecasting S\&P 500 stock index futures with a hybrid AI system’. Yenshan Tsaih , Hsu , C Charles , Lai . \textit{Decision Support Systems} 1998. 23 p. . \bibitem[Wong ()]{b39}\label{b39} ‘Fuzzy neural systems for stock selection’. F S Wong . \textit{Financial Analysts Journal} 1992. 48 p. . \bibitem[Steven et al. ()]{b32}\label{b32} ‘Graded forecasting using an array of bipolar predictions: application of probabilistic neural networks to a stock market index’. H Steven , Se Hak Kim , Chun . \textit{International Journal of Forecasting} 1998. 14 p. . \bibitem[Yao and Tan ()]{b41}\label{b41} ‘Guidelines for financial forecasting with neural networks’. J T Yao , C L Tan . \textit{Proceedings of the. International Conference on Neural Information Processing}, (the. International Conference on Neural Information ProcessingShanghai, China) 2001. \bibitem[Hiemstra ()]{b12}\label{b12} ‘Information Systems: Decision Support and Knowledge-Based Systems’. Y Hiemstra . \textit{Proceedings of the Twenty-Seventh Hawaii International Conference on System Sciences}, (the Twenty-Seventh Hawaii International Conference on System Sciences) 1994. 1994. III p. . (A stock market forecasting support system based on fuzzy logic) \bibitem[Goonatilake and Treleaven ()]{b11}\label{b11} \textit{Intelligent systems for finance and business}, S Goonatilake , P Treleaven . 1995. New York: Wiley. \bibitem[Sivanandam et al. ()]{b30}\label{b30} \textit{Introduction to Neural Networks using MATLAB 6.0}, S N Sivanandam , S Sumathi , S N Deepa . 2006. New Delhi: Tata McGraw-Hill Publishing Company Limited. \bibitem[Baestaens et al. ()]{b3}\label{b3} ‘Money market headline news flashes, effective news and the DEM/USD swap rate: An intraday analysis in operational time’. D E Baestaens , Van Den , W M Berg , H Vaudrey . \textit{Proc. 3rd Forecasting Financial Markets Conference}, (3rd Forecasting Financial Markets ConferenceLondon) 1995. \bibitem[Shih ()]{b29}\label{b29} ‘Neural nets in technical analysis’. Y L Shih . \textit{Technical Analysis of Stocks and Commodities} 1991. 9 (2) p. . \bibitem[Gately ()]{b10}\label{b10} \textit{Neural networks for financial forecasting}, E Gately . 1996. New York7 John Wiley \& Sons. \bibitem[Qi ()]{b23}\label{b23} ‘Nonlinear predictability of stock returns using financial and economic variables’. M Qi . \textit{Journal of Business and Economic Statistics} 1999. 17 p. . \bibitem[Virili and Reisleben ()]{b36}\label{b36} ‘Nonstationarity and data preprocessing for neural network predictions of an economic time series’. F Virili , B Reisleben . \textit{Proceedings of the International. Joint Conference on Neural Networks}, (the International. Joint Conference on Neural NetworksComo) 2000. 2000. 5 p. . \bibitem[Fama and French ()]{b7}\label{b7} ‘Permanent and Temporary Components of Stock Prices’. E F Fama , K R French . \textit{Journal of Political Economics} 1988a. 96 (2) p. . \bibitem[Pan (2003)]{b21}\label{b21} \textit{Proceedings of 2003 Hawaii International Performance Analysis of Stock Price Prediction using Artificial Neural Network Global Journal of Computer Science and Technology Volume XII Issue I Version}, H P Pan . 2003b. 25 January 2012. (A joint review of technical and quantitative analysis of the financial markets towards a unified science of intelligent finance) \bibitem[Refenes et al. ()]{b24}\label{b24} A P Refenes , Y Abu-Mostafa , J Moody . \textit{Proceedings of the 3 rd International Conference on Neural Networks in the Capital}, Markets, Weigend A (ed.) (the 3 rd International Conference on Neural Networks in the Capital) 1996. World Scientific. \bibitem[Utans and Moody ()]{b35}\label{b35} ‘Selecting neural network architectures via the prediction risk: application to corporate bond rating prediction’. J Utans , J E Moody . \textit{Proceedings of the 1st International. Conference on AI Applications on Wall Street}, (the 1st International. Conference on AI Applications on Wall Street) 1991. IEEE Computer Society Press. \bibitem[Serrano-Cinca ()]{b6}\label{b6} ‘Self organizing neural networks for financial diagnosis’. Carlos Serrano-Cinca . \textit{Decision Support Systems} 1996. 17 p. . \bibitem[Refenes ()]{b25}\label{b25} ‘Stock Performance Modeling Using Neural Networks: A Comparative Study With Regression Models’. Zapranis Refenes , Francis . \textit{Journal of Neural Networks} 1994. 1994. 7 (2) p. . \bibitem[Schoneburg ()]{b28}\label{b28} ‘Stock prediction using neural networks: A project report’. E Schoneburg . \textit{Neurocomputing} 1990. 2 p. . \bibitem[Kai Keng Ang and Chai Quek. ()]{b14}\label{b14} ‘Stock Trading Using RSPOP: A Novel Rough Set-Based Neuro-Fuzzy Approach’. \textit{IEEE Transactions of Neural Networks} Kai Keng Ang and Chai Quek. (ed.) 2006. 17 (5) p. . \bibitem[Pan ()]{b20}\label{b20} \textit{Swingtum -A computational theory of fractal dynamic swings and physical cycles of stock market in a quantum price-time space}, H P Pan . 2003a. (Ibid) \bibitem[Ward and Sherald (1995)]{b37}\label{b37} ‘The neural network financial wizards’. S Ward , M Sherald . \textit{Technical Analysis of Stocks and Commodities}, 1995. Dec. p. . \bibitem[Ruggerio (1994)]{b27}\label{b27} ‘Training neural nets for intermarket analysis’. M Ruggerio . \textit{Futures} 1994. Sep. p. . \bibitem[Abhyankar et al. ()]{b0}\label{b0} ‘Uncovering nonlinear structure in real-time stockmarket indexes: The S\&P 500, the DAX, the Nikkei 225, and the FTSE-100’. A Abhyankar , L S Copeland , W Wong . \textit{Journal of Business \& Economic Statistics} 1997. 15 p. . \bibitem[Kryzanowski et al. (1993)]{b17}\label{b17} ‘Using Artificial Neural Networks to Pick Stocks’. L Kryzanowski , M Galler , D W Wright . \textit{Financial Analysts Journal} 1993. July-August 1993. p. . \bibitem[Kean ()]{b16}\label{b16} ‘Using neural nets for intermarket analysis’. J Kean . \textit{Technical Analysis of Stocks and Commodities} 1992. 10 (11) . \bibitem[Fishman et al. ()]{b9}\label{b9} ‘Using neural nets in market analysis’. M B Fishman , D S Barr , W J Loick . \textit{Technical Analysis of Stocks and Commodities} 1991. 9 (4) p. . \bibitem[Wong and Selvi ()]{b40}\label{b40} B Wong , Y Selvi . \textit{Neural network applications in finance: A review and analysis of literature}, 1998. 1990-1996. 34 p. . \end{bibitemlist} \end{document}