CHAPTER 1 INTRODUCTION
Trade decisions on a stock market are made on the basis of predicting the
trend which it is driven by many direct and indirect factors. Effective
decisions depend on accurate prediction. Even though there have been many
empirical researches which deal with the issue of predicting stock price index;
most empirical findings are associated with the developed financial markets.
There are few researches exist in the literature to predict the direct of stock
price index movement in emerging markets, especially in Indonesian Stock
exchange. Accurate predictions of movement of stock price indexes are very
important for developing effective market trading strategies (Leung et al.
2000) the stock market is essentially dynamic, nonlinear, complicated,
nonparametric, and chaotic in nature (Abu-Mostafa & Atiya 1996). In
addition, stock market is affected by many macro economical factors such as
political events, firms’ policies, general economic conditions, investors’ expectations, institutional investors’ choices, movement of other stock market, and psychology of investors etc. (Tan et al. 2007).
So far, there are many techniques are applied to predict the market in order
to maximize profit and minimize risks, it can be categorized into four groups;
these techniques are included fundamental analysis, technical analysis, time
series analysis, and machine learning. The results from these techniques is
different, for example the fundamental analysis is used to define models which Trade decisions oon a stock market are made on ththe basis of predicting the
trend whhicich it is driven bby y mam nyny ddirecct and indirectt factors. Effective decicissions dependd on n acaccurate predictiion. EveEv n n ththouough there havve e been many empiricacal lreresesearchesswwhihich deal with the issueeoof fpredicctitingngsstotock priicece index; mo
mostst eempm iricicaal findings are associated with the develoopeped fifinanancnciaiall markrkets. Th
Theere arare few researches exist in the literature to predict ththe diirerectct of stocck pr
p icee index movement in emerging markets, especially in Indodonesisiann SStockk excchange. Accurate predictions of movement of stock price indeexes aarre vereryy
immportant for developing effective market trading strategies (LLeung etet all.
20
20000) the stock mamarkrketet is essentially y dydynanamimic, nonlinear, cocommplicateted,d, nonparametric, and chaotic iin n naatuture (Abu-Mostafa & Atiya 19966).). IInn ad
addition, stock market is affected by many macro economical facttorors susuchch as
po
p lilititicacall evevenentsts, , fifirmrms’s’ pololicicieies,s, ggenenereralal ecocononomimicc cocondndititioions, ininvevesstors’
ex
expepecttattiions,,ininsstitutional invevestors’ chohoiices, movemeentnt of fotthher sttocockk market,
and psychology of investors eetc. (Tan ett al. 2007).
So far, there are many techhniques arare applied to predict the market in order
to maximize profit and minimizee risksks, it can be categorized into four groups;
calculate the future price according to current indicators such as the gross
domestic product (GDP), consumer price index, interest rate and exchange
rate; the technical analysis is used for forecast the future price direction by
studying past market data - primarily stock price and volume. The technical
analysis basically use trading rules such as single moving trend, composite
moving trend, and channel breakout. However, these techniques don’t have ability to learn nonlinear variables as artificial intelligent (IA) approach does.
Artificial neural network (ANN) technique is one of data mining
techniques that is gaining increasing acceptance in the business area due to its
ability to learn and detect relationship among nonlinear variables. Also, it
allows deeper analysis of larger set of data especially those that have the
tendency to fluctuate within a short of period of time. If stock market return
fluctuations are affected by their recent historic behaviour, neural networks
which can model such temporal stock market changes can prove to be better
predictors (Tang et al. 1991). The elasticity and adaptability advantages of the
artificial neural network models have attracted the interest of many other
researchers (Adebiyi Ayodele A. et al 2012). Since the last decade, the
artificial neural network models have been used extensively in various
branches such as computer science, engineering, medical and criminal
diagnostics, biological investigation, analysing the business data, and
econometric analysis research. Also they can be used for analysing relations
among economic and financial phenomena, forecasting, data filtration, rate; the technical analysysisis iis used for ffororece ast the future price direction by
studying past mamarket data - primarily stock price anand volume. The technical
analysis bbasically use tradiinng rululess ssucuch h asas single movingng trend, composite moovving trend, annd d chchaannel breakout. Howeevever,r, tthehese techniqueess don’t have ability totolleaearnr nonlilinenear variables as artificialiintnteleligentt((IAIA) ) apa proachch does.
Ar
Arttificiiaal neural network (ANN) technique is onen of f dadatata minning te
techniqques that is gaining increasing acceptance in the businesss arereaa dudue e to itsts abilitity to learn and detect relationship among nonlinear variabbles. AAlsl o, it
alloows deeper analysis of larger set of data especially those thhat have ththee
tenndency to fluctuate within a short of period of time. If stockf mmarket rreturnrn
flucctuations aarere afffected byby ttheir recenentt hhistoric bbehehavaviour, neurral netwoorkrkss which can model such temporal ststoco k market changes can prove to bee bbetetteer pr
prededicictotorsrs((Tanggeett alal..191 91).) The elasticityyaandndaadadaptptability y adadvavantagageses oof f the ar
artitficial neuuraral l nenetwororkk modedelsls hhavave attrracacteted ththe e ininterest of mamanyny other researarchchererss ((Adebiyi Ayodelee A. et al 2012). Since ththee lalastst decade, the
artificial neural network mmodels havee been used extensively in various
branches such as computer sciencee, engineering, medical and criminal
diagnostics, biological investiggatioion, analysing the business data, and
generating financial time-series, and optimization (Shachmurove &
Witkowska 2000).
Why neural network is best for prediction? Because there are several
distinguished features that propound the use of neural network as a preferred
tool over other traditional models of prediction. Artificial neural networks are
nonlinear in nature and where most of the natural real world systems are non
linear in nature, artificial neural networks are preferred over the traditional
linear models. This is because the linear models generally fail to understand
the data pattern and analyse when the underlying system is a nonlinear one.
ANNs are data driven models. It has 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. The input variables are mapped to the output
variables by squashing or transforming by a special function known as
activation function. They independently learn the relationship inherent in the
variables from a set of labelled training example and therefore involves in
modification of the network parameters (Soni 2011).
It is of interest to study the extent of stock price index movement
predictability using data from emerging markets such as of the Indonesia stock
market.This emerging market’s performance is incredible for a long period of time. For example, in December 2002, composite index stand at 424.495
points, it was rapidly upwards to 2,745.826 at the end of 2007 and then
decreased to 1,135.408 at the end of 2008 (-50.64%) due to the impact of
global financial crisis and upwards again at the beginning of 2009 until Why neural netwoorkrk is best for predidictctioi n? Because there are several
distinguished fefeatures that propound the use of neuralal network as a preferred
tool oveverr other traditional momodedelsls oof f prprededicctitonon. Artificial neueural networks are noonnlinear inn naturree anand d where most of the natut raal l rer al wworld systeemsm are non linear inin nnatature, aartrtificial neural networks are prrefeferredd ovoverer tthe tradidtional liinenearar moddelels. This is because the linear models generalallyly faiil l toto uundersttana d th
the datata pattern and analyse when the underlying system is aa nononlilinenearar onee. A
ANNNs are data driven models. It has ability to discover nonlineaar relalatitiononship
in tthe input data set without a priori assumption of the knowledgee of relatiionon bettween the input and the output. The input variables are mapped too the ooutpuut
variriables byby ssququashing or trtransformimingng by a spececiaial functionn knownn aass activation function. They independndeently learn the relationship inherent inin tthhe
va
v ririabableless from aa ssetet oof f labelled training g exxamamplplee and thererefefororee innvovolvlveses in mo
modification ooff ththee netwtworork pararamemeteterrs (Sonnii202 111)).
It is of interest to studydy the extxtent of stock price index movement
predictability using data fromm emerging mmarkets such as of the Indonesia stock
market.This emerging market’s’ perforrmance is incredible for a long period of
November 2012, it reached 4,317. 277 points and 4,985.58 points on May 28,
2014. On an average day, transactions worth of between IDR 5 to 6 trillion
(US $520 million to US $620 million), and it has an average daily volume of
about six billion shares. In 2012, foreign investors purchased assets in the
Indonesian capital markets totaled IDR 19.55 trillion (about US $2 billion). In
the period of January to March in 2013, net foreign purchases already stood at
IDR 18.5 trillion nearly 100% increase comparing to the previous year, which
shows the attractiveness of these markets (David 2013). Market capitalization
has increased 412% from IDR 801 trillion in 2005 to IDR 4,099.34 trillion -
November 2012. In term of trade value, showed a significant increased after
2006 (US$ 49.4 billion) to US$114.9 billion in 2007 and quite stable since
then i.e. eleven months of 2012 totaled of US$104.6 billion.
There are very little previous researches exist (accessible) in related to
stock price prediction by using ANN techniques at IDX, such as Putra and
Kosala (2011) used ANN to predict intraday trading signals and Veri and
Baba (2013) forecasting the next closing price.
As we understand the characteristic that all stock markets, including IDX,
have in common is the uncertainty, which is related with their short and
long-term future state. This feature is undesirable for the investor but it is also
unavoidable whenever the stock market is selected as the investment tool. The
best that one can do is to try to reduce this uncertainty. In this research ANN
model is proposed to forecast the movement of stock price in the daily IDX
Index.
(US $520 million to US $$626200 million), anand dit has an average daily volume of
about six billioonn shares. In 2012, foreign investororss purchased assets in the Indonesiianan capital marketsttotoalaededIIDRDR119..555 trillion (aboutut UUS $2 billion). In the e pperiod of Januuararyy toto March in 2013, net foforereigign nppurchases alrereada y stood at IDR 188.5.5 ttririllllion neeararlly 100% increase compariringng to the e prprevevioi us yeaar,r, which shhowowssththe atttrtractiveness of these markets (David 2013). MarkeM ket t cacapipitat lizaatiton h
has incrreased 412% from IDR 801 trillion in 2005 to IDR 4,4,099.3.344 ttrillion -No
N veember 2012. In term of trade value, showed a significant inincreaeasesed d after 20006 (US$ 49.4 billion) to US$114.9 billion in 2007 and quite stablel sinncece
theen i.e. eleven months of 2012 totaled of US$104.6 billion.
There aree vevery little prrevevious reseaearrches exist t (a(accccessible) iin related d toto stock price prediction by using ANANN techniques at IDX, such as Puttrara aannd
Ko
Kosasalala ((202 11)) ususededdd AANNN to predict intradayay ttraradidngg sigignanalsls aand Vd Vereri i aand Ba
Baba (2013) )foforerecacastinngg ththe nextxtcclolosising priicece..
As we understand the chaararacteristiic cthat all stock markets, including IDX, have in common is the uncerrtainty, whicch is related with their short and
long-term future state. This featuree is unddesirable for the investor but it is also
1.1. Problem Identification
How to forecast the stock price index? The stock market index direction prediction is regarded as one of the crucial issues in recent financial analysis
studies (Wang & Choi 2013). Many techniques are employed to predict stock
prices in the stock markets but the past results are being questioned.
Generally, there are three schools of thought in terms of the ability to profit
from the equity market. The first school believes that no investor can achieve
above average trading advantages based on the historical and present
information. The major theories include the Random Walk Hypothesis and the
Efficient Market Hypothesis (Peters 1991). The Random Walk Hypothesis
states that prices on the stock market wander in a purely random and
unpredictable way. Each price change occurs without any influence by past
prices. The Efficient Market Hypothesis states that the markets fully reflect all
of the freely available information and prices are adjusted fully and
immediately once new information becomes available. If this is true then there
should not be any benefit for prediction, because the market will react and
compensate for any action made from these available information. The second
school’s view is the so-called fundamental analysis. It looks in depth at the financial conditions and operating results of a specific company and the
underlying behavior of its common stock. The value of a stock is established
by analysing the fundamental information associated with the company such
as accounting, competition, and management. The fundamental factors are
overshadowed by the speculators trading.
prediction is regarded as onone of the crucicialal issues in recent financial analysis
studies (Wang & & CChoi 2013). Many techniques are ememployed to predict stock
prices in n the stock markkeets s bubut t ththee papast results are bbeing questioned. Geennerally, there aaree thrh ee schools of thoughght inin ttererms of the abbilility to profit from thehe eeququiity maarkrkeet. The first school believeess that noo ininvevestsor cannaachieve abbovovee averraage trading advantages based on the hihistsorici alal aandnd preeses nt infformatation. The major theories include the Random Walk HyHypothhesesisis and thhe
Ef
E ficicient Market Hypothesis (Peters 1991). The Random Waalkl HHypypototheh sis stattes that prices on the stock market wander in a purely rrandom aandnd unnpredictable way. Each price change occurs without any influennce byy passt pr
pricices. The Efficiienentt MaMarkrketet Hypothesis ststatatesestthahatt ththe markets fullllyy reflect t aalll of the freely available informrmattioion and prices are adjusted fully y anandd
im
immem diately once new information becomes available. If this is truuee ththenen tthehere
sh
s ouldld nott bbe anany y bebenefit foforr prprededicictitioon, becaaususe e ththe markket will ret reacactt and coompmpensatetefforor any action maaded from ththese available ininfoformation.n.TThe second
school’s view is the so-calleed fundameental analysis. It looks in depth at the
financial conditions and opeerating resesults of a specific company and the
underlying behavior of its commmon sstock. The value of a stock is established
Technical analysis assumes that the stock market moves in trends and these
trends can be captured and used for forecasting. Technical analysis belongs to
the third school of thought. It attempts to use past stock price and volume
information to predict future price movements The technical analyst believes
that there are recurring patterns in the market behavior that are predictable. In
fact, there is not any research proved the existing of such patterns due to each
stock market has different characteristics, depending on the economies they
are related to, and varying from time to time. Most of the techniques used by
technical analysts have not been shown to be statistically valid and many lack
a rational explanation for their use. However, technical analysis has its value
on forecasting.
Artificial Neural Networks are regarded by many as one of the more suitable
techniques for stock market forecasting (Yao & Tan 2001). It has been
demonstrated to be an effective technique for capturing dynamic non-linear
relationships in stock markets, while technical analysis techniques unable to
do so.
1.2. Objective of the Research
The core objective of this research is to forecast the direction of movement in
the daily JKSE or IDX using artificial neural network, also to compare a
financial performance model and statistical model of ANN on its precision of
stock price prediction. At the same times, its empirical result will be
comparing with some recently researcher’s works in this market that used ANN models. Also, this research will seek to prove against a validity of the the third school of thoughghtt. IIt attemptst ttoo use past stock price and volume information to pprredict future price movements The e tetechnical analyst believes
that therere are recurring patteernns sininthethemmarkeket behavior that tara e predictable. In factct, there is notaanynyrrese earch proved the exististining g ofof such patternsns due to each stock mamarkrketet has ddififfeferent characteristics, depeendnding onon tthehe economimies they are e rerelalatted toto, and varying from time to time. Most of ththe techchniniququeses used dby technicah al analysts have not been shown to be statistically vallidid andd mmany lackck a
a ratitional explanation for their use. However, technical analysiiss has s ititss vav lue on fforecasting.
Arrtificial Neural Networks are regarded by many as one of the mmore ssuuitablle
techniquess fforor sstotockck mmararket t fof recasttining g (Y(Yaoao && TTanan 22001). It has bebeenen demonstrated to be an effective tetechnique for capturing dynamic nonn-lilineneaar
re
relal tiionnshshipipss inin sstotockck mmararkekets, while techchninicacall ananalalysysisis tectechnhniiquess ununabablee to do
do sso.
1.2. Objective of the Research
Efficient Market Hypothesis and the Random Walk Hypothesis for short-term
trading advantages in this stock market, which is considered as one of the
most important emerging markets in Asia.
1.3. Contribution of the Research
Recently, a number of researchers have explored artificial intelligence
techniques such as ANNs to solve financial problems significantly increased,
but most has targeted the United States market (Suchira Chaigusin, 2011).
There have been limited attempts to research stock markets of developing
economies such as Indonesia. At the beginning of this research, the author find
that there are some previous research using intelligent approach in this market,
but there are not many existing research using artificial neural network
technique, specifically, to predict the index movements of the JKSE.
The major contributions of this study are to demonstrate and verify the
predictability of stock price index direction using the financial and statistical
performances of ANN model. It also benefit to other researchers/students who
are interested in studying stock market price movement with ANN model.
This study is one step along the path towards applying ANN to the IDX in
order to clarify and predict stock performances. Enhancing the use of ANN in
financial areas and contributing incrementally to the growing knowledge base
of this financial forecasting field.
most important emerging gmamarkets in Asik iaa.
1.3. Contributionn of the Researchc
Rececently, a nuumbmbeer of reeseseaarchers h s hahaveve eexpxplolorred artificialal intelligence t
techniququeses suuch as ANNNNs to solve financialal pproroblems sisigngnifificicantly inincreased, buut momosts hass targeted the United States market (Sucht chira ChChaiaigugusin, 22010 1). Th
Theere hahave been limited attempts to research stock markekets oof f dedevvelopinng ec
e onoomies such as Indonesia. At the beginning of this research, tht e auauththoror findnddddd thatt there are some previous research using intelligent approach inn thissmmarkeett, buutt there are not many existing research using artificial neurral netwworkk
te
techchnique, specifically,y, to ppredict the index movements of the JKSEE..
The major contributions of thihis s ststudy are to demonstrate and verifify y ththe
pr
p ededicictatabilityy of stock prp ice index direction using g the financiaiall anandd ststatatisstitical
pe
performances ooff ANANN model. IIt t alalsoso bebenefit to oththerer rrese earchers/stutudedentnts who
are ininteterereststeded in studying stockk market t price movement wwitithh ANANNN model.
This study is one step alongg the path ttowards applying ANN to the IDX in
1.4. Scope of the Research
As there are many ANN research techniques were used to predict stock price
movement index mentioned in 1.1; some of recently research are using
international market indicators, technical & fundamental indicators as inputs
which it’s called “hybrid”. But some try to combined a lot of indicators as input variable. However, the research finding indicated that many indicators/
or higher number of input variables is not mean such forecasting technique
(model) will give a result more accuracy.
In this research, we will attempt to forecast daily stock price movement at
JKSE, using financial performance and statistical performance evaluations of
ANN models. The data collection with total period of 9 years and 5 months,
starting from January 3, 2005 to May 28, 2014. The reason we start from
2005 because the index prices at the beginning 2005 reached RP1.000 and has
dramatically increased until the end of 2007 and then in the direction of
decrease. At the beginning of 2009 index prices had in the direction of
increased again. So, we would like to see how ANN model perform in the
different period and direction. The data be divided into two separate sets, a
period of January 3, 2005 to December 30, 2010 is for network training
purposes. From January 3, 2005 to May 28, 2014 is for testing the predictive
ability of the network. A three-layered feed-forward ANN model will be
constructed (see Figure. 2). This ANN model consists of an input layer, a
hidden layer and an output layer, each of which is connected to the other.
Inputs for the network are twelve technical indicators which are represented
by twelve neurons in the input layer (see table 2).
movement index mentioneded iinn 11.1;1; ssomo e of recently research are using international markrkeet indicators, technical & fundadamem ntal indicators as inputs
which it’ss called “hybrid”. But some try to combined aa llot of indicators as
inpuutt variable. HoHowew vever, thee rese earch h fifinddinngg inindidicacated that manany indicators/ or higheer r nunumbm er of ininpput variables is nott mmeae n such ffororececasting ttece hnique (mmododelel))will ggivive a result more accuracy.
In thhisis research, we will attempt to forecast daily stock pprircemmovoveme ent ata JK
J SEE, using financial performance and statistical performance evalluau titionons off ANNNN models. The data collection with total period of 9 years annd 5 mmonthshs, staarting from January 3, 2005 to May 28, 2014. The reason wee start frfromm
20
2 005 because the index pprices at the beginningg 2005 reachedRP1.000000 and hhasas dramatically increased untild l tthehe endnd oof 2007 and then in the directionon oof de
d crease. At the beginning of 2009 index prices had in the dirireectitionn of
incrcreaeasesed d agagaiainn. SSo,o, wwee wowoululd d lilkee ttoo seseee hohow w ANANNN momodedel l peperfrforrm m inn the di
diffffererenentt peperiodod aand directionon. The daatata be dividedd ininto ttwowo ssepepararatate sets, a period of January 3, 2005 tto Decembber 30, 2010 is for network training
purposes. From January 3, 20005 to Maayy 28, 2014 is for testing the predictive
ability of the network. A threee-layeyered feed-forward ANN model will be
The forecasting ability of the ANN model is accessed by using
back-propagation neural network of errors such as MAE, RMSE, MAPE, and R2, to
improve their prediction performances two comprehensive parameter setting
experiments for both technical indicators and the levels of the index in the
market are performed. The logistic sigmoid transfer function will be used in
neural network; this function converts an input value to an output ranging
from 0 to 1 (see 2.3). If the connection weight is negative or (value < 0) then
tomorrow close price value < than today’s price (loss). If the value is positive (value > 0.5) then tomorrow close price value > than today’s price (profit).
As we want to see the direction of movement decrease or increase so the
output will be categorized as 0 and 1. Therefore, if the forecasting value
smaller than 0.5 it will be categorized as decreased direction.
Published stock data will be collected from Yahoo.Finance especially daily
closing price, daily high price, and daily low price of total price index.
1.5. Organization of the Thesis
This thesis is composed of six Chapters. The remaining portion of the thesis is
broken up into the following Chapters: Chapter 2 describes Artificial Neural
Network and related literature. Chapter 3 describes the research methodology
which includes ANN modeling, research data and technical input variables. In
Chapter 4 descriptive statistics are used simply to describe the sample.
Chapter 5 the empirical results are summarized and discussed. Chapter 6 brief
conclusion with some suggestions for the future work on the field of stock
market prediction
improve their prediction ppererfformances twtwo o comprehensive parameter setting
experiments for r bboth technical indicators and the lelevels of the index in the
market aarere performed. The lol gigststicc ssigigmomoidid transfer functitiono will be used in neurural network; ththisis ffunu ction converts an ininpuput t vavalue to an ouutptput ranging from 00ttoo 11(s(see 2.33)). If the connection weighthtiissnegatiiveveoor r (value << 0) then tomomorrrroow clolose price value < than today’s price (loss). IfIf the valalueue iis sposisitive (
(value >l > 0.5) then tomorrow close price value > than todayy’s prricice e (profit)t). As
A wwe want to see the direction of movement decrease or inncreaasese ssoo the outtput will be categorized as 0 and 1. Therefore, if the foreccasting valuluee
smmaller than 0.5 it will be categorized as decreased direction.
Pubblished stocockk ddata will bebe collectedd ffrom Yahoh o.oFiFinan nce espep cially ddaiailyly closing price, daily high price, andndddaily low price of total price index.
1.
1.5.5. OrOrgaganinizazatitiononooff ththee ThThesesisis
Th
Thisis thesis isisccomompoposesedd ofofssix ChChapapteters. TTheherrememaininingng pporo tion ooff ththee ththesis is broken up into the following CChapterrs:s Chapter 2 describes AArtificial Neural Network and related literaturre. Chapter 3 describes the research methodology
which includes ANN modelingg, researcch data and technical input variables. In