Dissertations / Theses on the topic 'Stock price prediction'
To see the other types of publications on this topic, follow the link: Stock price prediction.
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 dissertations / theses for your research on the topic 'Stock price prediction.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse dissertations / theses on a wide variety of disciplines and organise your bibliography correctly.
1
Ghodsi, Boushehri Ali. "Applying fuzzy logic to stock price prediction." Thesis, National Library of Canada = Bibliothèque nationale du Canada, 2000. http://www.collectionscanada.ca/obj/s4/f2/dsk1/tape3/PQDD_0015/MQ54332.pdf.
Full text
2
Eadie, Edward Norman. "Small resource stock share price behaviour and prediction." Title page, contents and abstract only, 2002. http://web4.library.adelaide.edu.au/theses/09CM/09cme11.pdf.
Full text
3
Wang, Nancy. "Spectral Portfolio Optimisation with LSTM Stock Price Prediction." Thesis, KTH, Matematisk statistik, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-273611.
Full textAbstract:
Nobel Prize-winning modern portfolio theory (MPT) has been considered to be one of the most important and influential economic theories within finance and investment management. MPT assumes investors to be riskaverse and uses the variance of asset returns as a proxy of risk to maximise the performance of a portfolio. Successful portfolio management reply, thus on accurate risk estimate and asset return prediction. Risk estimates are commonly obtained through traditional asset pricing factor models, which allow the systematic risk to vary over time domain but not in the frequency space. This approach can impose limitations in, for instance, risk estimation. To tackle this shortcoming, interest in applications of spectral analysis to financial time series has increased lately. Among others, the novel spectral portfolio theory and the spectral factor model which demonstrate enhancement in portfolio performance through spectral risk estimation [1][11]. Moreover, stock price prediction has always been a challenging task due to its non-linearity and non-stationarity. Meanwhile, Machine learning has been successfully implemented in a wide range of applications where it is infeasible to accomplish the needed tasks traditionally. Recent research has demonstrated significant results in single stock price prediction by artificial LSTM neural network [6][34]. This study aims to evaluate the combined effect of these two advancements in a portfolio optimisation problem and optimise a spectral portfolio with stock prices predicted by LSTM neural networks. To do so, we began with mathematical derivation and theoretical presentation and then evaluated the portfolio performance generated by the spectral risk estimates and the LSTM stock price predictions, as well as the combination of the two. The result demonstrates that the LSTM predictions alone performed better than the combination, which in term performed better than the spectral risk alone.Den nobelprisvinnande moderna portföjlteorin (MPT) är utan tvekan en av de mest framgångsrika investeringsmodellerna inom finansvärlden och investeringsstrategier. MPT antar att investerarna är mindre benägna till risktagande och approximerar riskexponering med variansen av tillgångarnasränteavkastningar. Nyckeln till en lyckad portföljförvaltning är därmed goda riskestimat och goda förutsägelser av tillgångspris. Riskestimering görs vanligtvis genom traditionella prissättningsmodellerna som tillåter risken att variera i tiden, dock inte i frekvensrummet. Denna begränsning utgör bland annat ett större fel i riskestimering. För att tackla med detta har intresset för tillämpningar av spektraanalys på finansiella tidsserier ökat de senast åren. Bland annat är ett nytt tillvägagångssätt för att behandla detta den nyintroducerade spektralportföljteorin och spektralfak- tormodellen som påvisade ökad portföljenprestanda genom spektralriskskattning [1][11]. Samtidigt har prediktering av aktierpriser länge varit en stor utmaning på grund av dess icke-linjära och icke-stationära egenskaper medan maskininlärning har kunnat använts för att lösa annars omöjliga uppgifter. Färska studier har påvisat signifikant resultat i aktieprisprediktering med hjälp av artificiella LSTM neurala nätverk [6][34]. Detta arbete undersöker kombinerade effekten av dessa två framsteg i ett portföljoptimeringsproblem genom att optimera en spektral portfölj med framtida avkastningar predikterade av ett LSTM neuralt nätverk. Arbetet börjar med matematisk härledningar och teoretisk introduktion och sedan studera portföljprestation som genereras av spektra risk, LSTM aktieprispredikteringen samt en kombination av dessa två. Resultaten visar på att LSTM-predikteringen ensam presterade bättre än kombinationen, vilket i sin tur presterade bättre än enbart spektralriskskattningen.
4
Karlsson, Nils. "Comparison of linear regression and neural networks for stock price prediction." Thesis, Uppsala universitet, Signaler och system, 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-445237.
Full textAbstract:
Stock market prediction has been a hot topic lately due to advances in computer technology and economics. One economic theory, called Efficient Market Hypothesis (EMH), states that all known information is already factored into the prices which makes it impossible to predict the stock market. Despite the EMH, many researchers have been successful in predicting the stock market using neural networks on historical data. This thesis investigates stock prediction using both linear regression and neural networks (NN), with a twist. The inputs to the proposed methods are a number of profit predictions calculated with stochastic methods such as generalized autoregressive conditional heteroskedasticity (GARCH) and autoregressive integrated moving average (ARIMA). By contrast the traditional approach was instead to use raw data as inputs. The proposed methods show superior result in yielding profit: at best 1.1% in the Swedish market and 4.6% in the American market. The neural network yielded more profit than the linear regression model, which is reasonable given its ability to find nonlinear patterns. The historical data was used with different window sizes. This gives a good understanding of the window size impact on the prediction performance.
5
Burgard, Andrew. "Can Business News Provide Insight into a Stock’s Future Price Performance?" Scholarship @ Claremont, 2017. http://scholarship.claremont.edu/cmc_theses/1673.
Full textAbstract:
Mutual funds and money managers have recently come under fire for their inability to beat market level returns since the Great Recession. With the recent trend towards passive money management through ETFs and other market-based securities, many investors have come to doubt whether above market returns are realizable in today’s economic climate. This paper examines whether business news has any predictable impact on stock price. Specifically, the paper explores the impact of analyst reports, mergers & acquisition news, legal affairs, insider buying and selling and changes to executive leadership on a stock’s excess returns. The results show that optimistic analyst ratings are correlated with positive excess returns before, during, and after the ratings are released. Furthermore, pessimistic analyst ratings are correlated with negative excess returns over the same time frame. These results provide support for a short term trading strategy that mirrors analyst opinions.
6
Troeman, Reamflar Elvio Estebano, and Lisa Fischer. "Politics, Artificial Intelligence, Twitter and Stock Return : An Interdisciplinary Test for Stock Price Prediction Based on Political Tweets." Thesis, Internationella Handelshögskolan, Jönköping University, IHH, Företagsekonomi, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:hj:diva-48436.
Full textAbstract:
As the world is gravitating toward an information economy, it has become more and more critical for an investor to understand the impact of data and information. One of the sources of data that can be converted into information are texts from microblogging platforms, such as Twitter. The user of such a microblogging account can filtrate opinion and information to millions of people. Depending on the account holder, the opinion or information originated from the designated account may lead to different societal impact. The microblogging scope of this investigation are politicians holding a Twitter account. This investigation will look into the relationship between political tweets' sentiment and market movement and the subsequent longevity of such an effect. The classified sentiments are positive or negative. The presence of artificial intelligence is vital for a data-driven investigation; in the context of this investigation, artificial intelligence will be used to classify the sentiment of the political tweet. The methods chose to assess the impact of a political tweet and market movement is event-study. The impact is expressed in either a positive or a negative cumulative abnormal return subsequent to the political tweet. The findings of the investigation indicate that on average, there is no statistical evidence that a political tweets' sentiment leads to an abnormal return. However, in specific cases, political tweet leads to abnormal return. Moreover, it has been determined that the longevity of the effect is rather short. This is an interdisciplinary approach that can be applied by individual and institutional investors and financial institutions.
7
Van, Niekerk J. P. de T. "The application of neural networks to the prediction of share price indices on the JSE." Thesis, Stellenbosch : Stellenbosch University, 2002. http://hdl.handle.net/10019.1/53086.
Full textAbstract:
Thesis (MBA)--Stellenbosch University, 2002.ENGLISH ABSTRACT: The dream of finding the ultimate tool for forecasting market instruments like share prices has long eluded investors throughout the world. Various forecasting techniques have been examined with a view to helping the investor or analyst to gain a better understanding of price behaviour in the open market. These techniques have been based mainly on traditional statistical analysis of data to forecast price behaviour. Though used by almost all serious investors, these techniques have yielded limited success as investment instruments. The reason for this is that most of these methods explored linear relationships between variables in the forecasting model, while in fact, most relationships found between variables in the share market are non-linear. Neural networks present a unique opportunity for the investor to overcome this problem. Neural networks are mathematical models of the human brain and have the ability to map complex nonlinear relationships between data sets. This study focuses on developing a neural network model to predict the price changes of the ALSI index on the JSE one and five days into the future. The results of the neural network model were then compared to forecasting results obtained by using a traditional statistical forecasting technique namely ARIMA modelling. The study found that the neural network models did not significantly perform better than the ARIMA models. A further test was done to determine the performance of the five-day forecasting model when analysing different time windows within the given data set. The test indicated that the model did perform better when using the inputs of certain time frames. This indicates that the neural network model needs to be updated regularly to ensure optimum model performance. The results of the neural network models were also used in a trading simulation to determine whether these results could be applied successfully to trading the ALSI index on the JSE. Unfortunately, the results of the trading simulation showed that using the neural network results as trading strategy yielded poorer results than using a buy/hold investment strategy. It can therefore be concluded that, although the neural network models performed relatively well relative to traditional forecasting techniques in forecasting the ALSI index, the forecasts were still not accurate enough to be useful as inputs in a trading strategy.
AFRIKAANSE OPSOMMING: Die droom om die perfekte vooruitskattingsinstrument te vind om die prysgedrag van verskillende markinstrumente vooruit te skat, ontwyk al generasies lank die meeste beleggers. Verskillende tegnieke is al ondersoek om die belegger te help om ’n beter gevoel van prysveranderinge in die vrye mark te verkry. Die meeste van hierdie tegnieke het gefokus op tradisionele statistiese vooruitskattingstegnieke. Alhoewel hierdie tegnieke wêreldwyd deur investeerders gebruik word, was hierdie metodes se sukses as investeringsinstrument beperk. Die rede vir hierdie beperkte sukses lê in die feit dat hierdie tegnieke slegs die lineêre verwantskappe tussen veranderlikes gebruik het om voorspellings te maak, terwyl die meeste verwantskappe wat tussen veranderlikes in die vrye mark bestaan, nie-lineêr is. Neurale netwerke bied ’n unieke geleentheid vir beleggers om bogenoemde probleme te oorkom. Neurale netwerke is wiskundige modelle wat op die werking van die menslike brein gebaseer is en besit die vermoë om komplekse nie-lineêre verwantskappe tussen datastelle te herken. Hierdie studie fokus op die ontwikkeling van ’n neurale netwerk(e) om die prysverandering van die ALSI indeks op die JEB een en vyf dae in die toekoms vooruit te skat. Die resultate van die neurale netwerk model is verder vergelyk met die resultate van tradisionele statistiese vooruitskattingstegnieke soos byvoorbeeld ARIMA tegnieke. Die studie het gevind dat die neurale netwerk modelle nie beduidend beter gevaar het as die ARIMA modelle in die vooruitskatting van die ALSI indeks in beide die een- en vyfdag vooruitskattings nie. ’n Verdere toets is gedoen om die toepaslikheid van die gekose vyfdagmodel op verskillende tydvensters van die tydreeks te bepaal. Die toets het aangetoon dat die model baie meer akkuraat is vir sekere tydvensters as vir ander tydvensters. Dit dui dus daarop dat die neurale netwerk model gereeld heropgelei behoort te word om seker te maak dat die model optimaal presteer gegewe die spesifieke insetdata. Die resultate van die neurale netwerk model is ook gebruik in ’n simulasie om te bepaal of die resultate die belegger kan help om beter investeringsbesluite rakende die ALSI indeks op die JEB te maak. Ongelukkig het die simulasie resultate gewys dat ’n beleggingstrategie gebaseer op die neurale netwerk resultate swakker opbrengste gerealiseer het as ’n koop/hou beleggingstrategie. Ten slotte het die studie getoon dat alhoewel die neurale netwerk modelle relatief goed in vergelyking met tradisionele statistiese modelle gevaar het in die vooruitskatting van die ALSI indeks, hierdie vooruitskattings nie akkuraat genoeg is om as inset tot ’n investeringstrategie gebruik te word nie.
8
Karlemstrand, Roderick, and Ebba Leckström. "Using Twitter Attribute Information to Predict Stock Prices." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-299835.
Full textAbstract:
Being able to predict stock prices might be the unspoken wish of stock investors. Although stock prices are complicated to predict, there are many theories about what affects their movements, including interest rates, news and social media. With the help of Machine Learning, complex patterns in data can be identified beyond the human intellect. In this thesis, a Machine Learning model for time series forecasting is created and tested to predict stock prices. The model is based on a neural network with several layers of Long Short-Term Memory (LSTM) and fully connected layers. It is trained with historical stock values, technical indicators and Twitter attribute information retrieved, extracted and calculated from posts on the social media platform Twitter. These attributes are sentiment score, favourites, followers, retweets and if an account is verified. To collect data from Twitter, Twitter’s API is used. Sentiment analysis is conducted with Valence Aware Dictionary and sEntiment Reasoner (VADER). The results show that by adding more Twitter attributes, the Mean Squared Error (MSE) between the predicted prices and the actual prices improved by 3%. With technical analysis taken into account, MSE decreases from 0.1617 to 0.1437, which is an improvement of around 11%. The restrictions of this study include that the selected stock has to be publicly listed on the stock market and popular on Twitter and among individual investors. Besides, the stock markets’ opening hours differ from Twitter, which constantly available. It may therefore introduce noises in the model.Att kunna förutspå aktiekurser kan sägas vara aktiespararnas outtalade önskan. Även om aktievärden är komplicerade att förutspå finns det många teorier om vad som påverkar dess rörelser, bland annat räntor, nyheter och sociala medier. Med hjälp av maskininlärning kan mönster i data identifieras bortom människans intellekt. I detta examensarbete skapas och testas en modell inom maskininlärning i syfte att beräkna framtida aktiepriser. Modellen baseras på ett neuralt nätverk med flera lager av LSTM och fullt kopplade lager. Den tränas med historiska aktievärden, tekniska indikatorer och Twitter-attributinformation. De är hämtad, extraherad och beräknad från inlägg på den sociala plattformen Twitter. Dessa attribut är sentiment-värde, antal favorit-markeringar, följare, retweets och om kontot är verifierat. För att samla in data från Twitter används Twitters API och sentimentanalys genomförs genom VADER. Resultatet visar att genom att lägga till fler Twitter attribut förbättrade MSE mellan de förutspådda värdena och de faktiska värdena med 3%. Genom att ta teknisk analys i beaktande minskar MSE från 0,1617 till 0,1437, vilket är en förbättring på 11%. Begränsningar i denna studie innefattar bland annat att den utvalda aktien ska vara publikt listad på börsen och populär på Twitter och bland småspararna. Dessutom skiljer sig aktiemarknadens öppettider från Twitter då den är ständigt tillgänglig. Detta kan då introducera brus i modellen.
9
Kennedy, Pauline. "Three essays on the prediction and identification of currency crises /." Diss., Connect to a 24 p. preview or request complete full text in PDF format. Access restricted to UC campuses, 2003. http://wwwlib.umi.com/cr/ucsd/fullcit?p3102540.
Full text
10
Yin, Pei. "Volatility estimation and price prediction using a hidden Markov model with empirical study." Diss., Columbia, Mo. : University of Missouri-Columbia, 2007. http://hdl.handle.net/10355/4795.
Full textAbstract:
Thesis (Ph. D.)--University of Missouri-Columbia, 2007.The entire dissertation/thesis text is included in the research.pdf file; the official abstract appears in the short.pdf file (which also appears in the research.pdf); a non-technical general description, or public abstract, appears in the public.pdf file. Title from title screen of research.pdf file (viewed on December 18, 2007) Vita. Includes bibliographical references.
11
Alam, Joy, and Jesper Ljungehed. "A comparative study of hybrid artificial neural network models for one-day stock price prediction." Thesis, KTH, Skolan för datavetenskap och kommunikation (CSC), 2015. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-166641.
Full textAbstract:
Prediction of stock prices is an important financial problem that is receiving increased attention in the field of artificial intelligence. Many different neural network and hybrid models for obtaining accurate prediction results have been proposed during the last few years in an attempt to outperform the traditional linear and nonlinear approaches. This study evaluates the performance of three different hybrid neural network models used for one-day stock close price prediction; a pre-processed evolutionary Levenberg-Marquardt neural network, Bayesian regularized artificial neural network and neural network with technical- and fractal analysis. It was also determined which of the three outperformed the others. The performance evaluation and comparison of the models are done using statistical error measures for accuracy; mean square error, symmetric mean absolute percentage error and point of change in direction. The results indicate good performance values for the Bayesian regularized artificial neural network, and varied performance for the others. Using the Friedman test, one model clearly is different in its performance relative to the others, probably the above mentioned model. The results for two of the models showed a large standard deviation of the error measurements which indicates that the results are not entirely reliable.
12
Gottschling, Andreas Peter. "Three essays in neural networks and financial prediction /." Diss., Connect to a 24 p. preview or request complete full text in PDF format. Access restricted to UC campuses, 1997. http://wwwlib.umi.com/cr/ucsd/fullcit?p9728773.
Full text
13
Li, Qi. "Application of Improved Feature Selection Algorithm in SVM Based Market Trend Prediction Model." Thesis, Portland State University, 2019. http://pqdtopen.proquest.com/#viewpdf?dispub=10979352.
Full textAbstract:
In this study, a Prediction Accuracy Based Hill Climbing Feature Selection Algorithm (AHCFS) is created and compared with an Error Rate Based Sequential Feature Selection Algorithm (ERFS) which is an existing Matlab algorithm. The goal of the study is to create a new piece of an algorithm that has potential to outperform the existing Matlab sequential feature selection algorithm in predicting the movement of S&P 500 (
GSPC) prices under certain circumstances. The twoalgorithms are tested based on historical data of
GSPC, and SupportVector Machine (SVM) is employed by both as the classifier. A prediction without feature selection algorithm implemented is carried out and used as a baseline for comparison between the two algorithms. The prediction horizon set in this study for both algorithms varies from one to 60 days. The study results show that AHCFS reaches higher prediction accuracy than ERFS in the majority of the cases.
14
Brimble, Mark Andrew, and m. brimble@griffith edu au. "The Relevance of Accounting Information for Valuation and Risk." Griffith University. School of Accounting, Banking and Finance, 2003. http://www4.gu.edu.au:8080/adt-root/public/adt-QGU20030829.120234.
Full textAbstract:
A key theme in capital markets research examines the relationships between accounting information and firm value. Two concerns relating to the value relevance of accounting information are: (1) concerns over the explanatory and predictive power of the evidence presented in the prior literature (Lev, 1989); and (2) the evidence of a deterioration in the association between accounting information and stock prices over the past four decades (Collins, Maydew and Weiss, 1997; Francis and Schipper, 1999; Lev and Zarowin, 1999). These concerns provide the key motivation for this thesis which examines: (1) the usefulness of the clean surplus accounting equation in valuation; (2) the role of accounting information in estimating and predicting systematic risk and; (3) the changing nature of the relationship between accounting information, stock prices and risk over time. The empirical research provides evidence of the value-irrelevance of the clean surplus equation and that controlling for the functional form of the earnings-returns relationship is more important. Evidence is also provided that accounting variables are highly associated with M-GARCH risk betas and also possess predictive ability relative to these risk measures. Finally, the relationships between stock prices, risk models and accounting information are shown to have not deteriorated over time, contrary to prior evidence. Rather, the functional form of the relationship has changed from linear to a non-linear arctan association. Overall, accounting information continues to play the central role in the determination of stock prices and risk metrics.
15
Brimble, Mark Andrew. "The Relevance of Accounting Information for Valuation and Risk." Thesis, Griffith University, 2003. http://hdl.handle.net/10072/365276.
Full textAbstract:
A key theme in capital markets research examines the relationships between accounting information and firm value. Two concerns relating to the value relevance of accounting information are: (1) concerns over the explanatory and predictive power of the evidence presented in the prior literature (Lev, 1989); and (2) the evidence of a deterioration in the association between accounting information and stock prices over the past four decades (Collins, Maydew and Weiss, 1997; Francis and Schipper, 1999; Lev and Zarowin, 1999). These concerns provide the key motivation for this thesis which examines: (1) the usefulness of the clean surplus accounting equation in valuation; (2) the role of accounting information in estimating and predicting systematic risk and; (3) the changing nature of the relationship between accounting information, stock prices and risk over time. The empirical research provides evidence of the value-irrelevance of the clean surplus equation and that controlling for the functional form of the earnings-returns relationship is more important. Evidence is also provided that accounting variables are highly associated with M-GARCH risk betas and also possess predictive ability relative to these risk measures. Finally, the relationships between stock prices, risk models and accounting information are shown to have not deteriorated over time, contrary to prior evidence. Rather, the functional form of the relationship has changed from linear to a non-linear arctan association. Overall, accounting information continues to play the central role in the determination of stock prices and risk metrics.Thesis (PhD Doctorate)
Doctor of Philosophy (PhD)
School of Accounting, Banking and Finance
Full Text
16
Zhai, Yuzheng. "Improving scalability and accuracy of text mining in grid environment." Connect to thesis, 2009. http://repository.unimelb.edu.au/10187/5927.
Full textAbstract:
The advance in technologies such as massive storage devices and high speed internet has led to an enormous increase in the volume of available documents in electronic form. These documents represent information in a complex and rich manner that cannot be analysed using conventional statistical data mining methods. Consequently, text mining is developed as a growing new technology for discovering knowledge from textual data and managing textual information. Processing and analysing textual information can potentially obtain valuable and important information, yet these tasks also requires enormous amount of computational resources due to the sheer size of the data available. Therefore, it is important to enhance the existing methodologies to achieve better scalability, efficiency and accuracy.The emerging Grid technology shows promising results in solving the problem of scalability by splitting the works from text clustering algorithms into a number of jobs, each to be executed separately and simultaneously on different computing resources. That allows for a substantial decrease in the processing time and maintaining the similar level of quality at the same time.
To improve the quality of the text clustering results, a new document encoding method is introduced that takes into consideration of the semantic similarities of the words. In this way, documents that are similar in content will be more likely to be group together.
One of the ultimate goals of text mining is to help us to gain insights to the problem and to assist in the decision making process together with other source of information. Hence we tested the effectiveness of incorporating text mining method in the context of stock market prediction. This is achieved by integrating the outcomes obtained from text mining with the ones from data mining, which results in a more accurate forecast than using any single method.
17
Badenhorst, Dirk Jakobus Pretorius. "Improving the accuracy of prediction using singular spectrum analysis by incorporating internet activity." Thesis, Stellenbosch : Stellenbosch University, 2013. http://hdl.handle.net/10019.1/80056.
Full textAbstract:
Thesis (MComm)--Stellenbosch University, 2013.ENGLISH ABSTRACT: Researchers and investors have been attempting to predict stock market activity for years. The possible financial gain that accurate predictions would offer lit a flame of greed and drive that would inspire all kinds of researchers. However, after many of these researchers have failed, they started to hypothesize that a goal such as this is not only improbable, but impossible. Previous predictions were based on historical data of the stock market activity itself and would often incorporate different types of auxiliary data. This auxiliary data ranged as far as imagination allowed in an attempt to find some correlation and some insight into the future, that could in turn lead to the figurative pot of gold. More often than not, the auxiliary data would not prove helpful. However, with the birth of the internet, endless amounts of new sources of auxiliary data presented itself. In this thesis I propose that the near in finite amount of data available on the internet could provide us with information that would improve stock market predictions. With this goal in mind, the different sources of information available on the internet are considered. Previous studies on similar topics presented possible ways in which we can measure internet activity, which might relate to stock market activity. These studies also gave some insights on the advantages and disadvantages of using some of these sources. These considerations are investigated in this thesis. Since a lot of this work is therefore based on the prediction of a time series, it was necessary to choose a prediction algorithm. Previously used linear methods seemed too simple for prediction of stock market activity and a new non-linear method, called Singular Spectrum Analysis, is therefore considered. A detailed study of this algorithm is done to ensure that it is an appropriate prediction methodology to use. Furthermore, since we will be including auxiliary information, multivariate extensions of this algorithm are considered as well. Some of the inaccuracies and inadequacies of these current multivariate extensions are studied and an alternative multivariate technique is proposed and tested. This alternative approach addresses the inadequacies of existing methods. With the appropriate methodology chosen and the appropriate sources of auxiliary information chosen, a concluding chapter is done on whether predictions that includes auxiliary information (obtained from the internet) improve on baseline predictions that are simply based on historical stock market data.
AFRIKAANSE OPSOMMING: Navorsers en beleggers is vir jare al opsoek na maniere om aandeelpryse meer akkuraat te voorspel. Die moontlike finansiële implikasies wat akkurate vooruitskattings kan inhou het 'n vlam van geldgierigheid en dryf wakker gemaak binne navorsers regoor die wêreld. Nadat baie van hierdie navorsers onsuksesvol was, het hulle begin vermoed dat so 'n doel nie net onwaarskynlik is nie, maar onmoontlik. Vorige vooruitskattings was bloot gebaseer op historiese aandeelprys data en sou soms verskillende tipes bykomende data inkorporeer. Die tipes data wat gebruik was het gestrek so ver soos wat die verbeelding toegelaat het, in 'n poging om korrelasie en inligting oor die toekoms te kry wat na die guurlike pot goud sou lei. Navorsers het gereeld gevind dat hierdie verskillende tipes bykomende inligting nie van veel hulp was nie, maar met die geboorte van die internet het 'n oneindige hoeveelheid nuwe bronne van bykomende inligting bekombaar geraak. In hierdie tesis stel ek dus voor dat die data beskikbaar op die internet dalk vir ons kan inligting gee wat verwant is aan toekomstige aandeelpryse. Met hierdie doel in die oog, is die verskillende bronne van inligting op die internet gebestudeer. Vorige studies op verwante werk het sekere spesifieke maniere voorgestel waarop ons internet aktiwiteit kan meet. Hierdie studies het ook insig gegee oor die voordele en die nadele wat sommige bronne inhou. Hierdie oorwegings word ook in hierdie tesis bespreek. Aangesien 'n groot gedeelte van hierdie tesis dus gebasseer word op die vooruitskatting van 'n tydreeks, is dit nodig om 'n toepaslike vooruitskattings algoritme te kies. Baie navorsers het verkies om eenvoudige lineêre metodes te gebruik. Hierdie metodes het egter te eenvoudig voorgekom en 'n relatiewe nuwe nie-lineêre metode (met die naam "Singular Spectrum Analysis") is oorweeg. 'n Deeglike studie van hierdie algoritme is gedoen om te verseker dat die metode van toepassing is op aandeelprys data. Verder, aangesien ons gebruik wou maak van bykomende inligting, is daar ook 'n studie gedoen op huidige multivariaat uitbreidings van hierdie algoritme en die probleme wat dit inhou. 'n Alternatiewe multivariaat metode is toe voorgestel en getoets wat hierdie probleme aanspreek. Met 'n gekose vooruitskattingsmetode en gekose bronne van bykomende data is 'n gevolgtrekkende hoofstuk geskryf oor of vooruitskattings, wat die bykomende internet data inkorporeer, werklik in staat is om te verbeter op die eenvoudige vooruitskattings, wat slegs gebaseer is op die historiese aandeelprys data.
18
Andersson, Jesper, and Joakim Söderqvist. "Effekten av IAS 19 för värderingsmodellernas prognostiseringsförmåga och det observerade aktiepriset." Thesis, Södertörns högskola, Företagsekonomi, 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:sh:diva-38356.
Full textAbstract:
Denna kandidatuppsats testar förmånsredovisningen IAS 19 på marknadens observerade aktiepris för företag listade på OMX30. Syftet är att analysera effekten av IAS 19R på tre absoluta aktievärderingsmodeller, diskonterade kassaflödesmodellen, utdelningsdiskonteringsmodellen och residualvinstmodellen. Dessutom, om löner och annan ersättning samt avsättningar till pension inom IAS 19 har haft en positiv effekt på de observerade aktiepriserna. Metoderna som har använts för att testa precisionen av modellerna är reella och absoluta prognosfeltermsberäkningar. Vidare, för att testa effekten av anställningsförmåner, aktievärderingsmodellerna och IAS 19 på det observerade aktiepriset genomförs en multipel regressionsanalys med paneldata mellan åren 2009–2017. Regressionsmodellen inkluderar 22 företag listade på OMX30 per den 1a juli 2009. Inom det ekonometriska ramverket, har fyra stycken regressioner, med fasta effekter testats. Resultaten tyder på att förmånsredovisningen, IAS 19, inte har någon signifikant påverkan på det observerade aktiepriset. Däremot, i motsats med tidigare forskning, visar resultaten att löner och bonusar har en positiv effekt på de observerade aktiepriserna för företag listade på OMX30.This Bachelor thesis examines the employee benefits accounting IAS 19 on market share prices for companies listed on OMX30. The purpose is to analyze the effect of IAS 19R on three absolute valuation methods, Discounted Cash Flow, Dividend Discount and Residual Income valuation models. Also, what effect salaries, wages and defined benefits obligations in firms consolidated financial statements have had a positive effect on the market share price. The models which have been used to examine the predictability in the stock price valuations in the thesis are estimated using signed and absolute prediction errors. Furthermore, to examine the effect of employee benefits, share valuation models and IAS 19 on market share price a panel data between 2009-2017 have been used. The model includes 22 listed companies on OMX30 as of the 1stof July 2009. Within the econometric framework, four regressions have been applied, all with fixed effects. The results suggest that the employee benefits accounting have no significant impact on market share prices. However, in contrast to previous research, results show that salaries and wages have a positive impact on market share price for companies listed on OMX30.
19
Gao, Zhiyuan, and Likai Qi. "Predicting Stock Price Index." Thesis, Halmstad University, Applied Mathematics and Physics (CAMP), 2010. http://urn.kb.se/resolve?urn=urn:nbn:se:hh:diva-3784.
Full textAbstract:
This study is based on three models, Markov model, Hidden Markov model and the Radial basis function neural network. A number of work has been done before about application of these three models to the stock market. Though, individual researchers have developed their own techniques to design and test the Radial basis function neural network. This paper aims to show the different ways and precision of applying these three models to predict price processes of the stock market. By comparing the same group of data, authors get different results. Based on Markov model, authors find a tendency of stock market in future and, the Hidden Markov model behaves better in the financial market. When the fluctuation of the stock price index is not drastic, the Radial basis function neural network has a nice prediction.
20
Law, Ka-chung, and 羅家聰. "A comparison of volatility predictions in the HK stock market." Thesis, The University of Hong Kong (Pokfulam, Hong Kong), 1999. http://hub.hku.hk/bib/B30163535.
Full text
21
Lidén, Joel. "Stock Price Predictions using a Geometric Brownian Motion." Thesis, Uppsala universitet, Tillämpad matematik och statistik, 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-353586.
Full text
22
Tilakaratne, Chandima University of Ballarat. "Stock market predictions based on quantified intermarket influences." University of Ballarat, 2007. http://archimedes.ballarat.edu.au:8080/vital/access/HandleResolver/1959.17/12798.
Full textAbstract:
This research investigated the feasibility and capability of neural network-based approaches for predicting the direction of the Australian Stock market index (the target market). It includes several aspects: univariate feature selection from the historical time series of the target market, inter-market analysis for finding the most relevant influential markets, investigations of the effect of time cycles on the target market and the discovery of the optimal neural network architectures. Previous research on US stock markets and other international markets have shown that the neural network approach is one of most powerful techniques for predicting stock market behaviour. Neural networks are capable of capturing the non-linear stochastic and chaotic patterns in the stock market time series data. This study discovered that the relative return series of the Open, High, Low and Close prices of the target market, show 6-day cycles during the studied period of about 14 years. Multi-layer feedforward neural networks trained with a backpropagation algorithm were used for the experiments. Two major testing methods: testing with randomly selected test data and forward testing, were examined and compared. The best neural network developed in this study has achieved 87%, 81% 83% and 81% accuracy respectively in predicting the next-day direction of the relative return of the Open, High, Low and Close prices of the target market. The architecture of this network consists of 33 input features, one hidden layer with 3 neurons and 4 output neurons. The best input features set includes the relative returns from 1 to 6 days in the past of the Open, High, Low and Close prices of the target market, the day of the week, and the previous day’s relative return of the Close prices of the US S&P 500 Index, US Dow Jones Industrial Average Index, US Gold/Silver Index, and the US Oil Index.Doctor of Philosophy
23
Tilakaratne, Chandima. "Stock market predictions based on quantified intermarket influences." Thesis, University of Ballarat, 2007. http://researchonline.federation.edu.au/vital/access/HandleResolver/1959.17/58733.
Full textAbstract:
This research investigated the feasibility and capability of neural network-based approaches for predicting the direction of the Australian Stock market index (the target market). It includes several aspects: univariate feature selection from the historical time series of the target market, inter-market analysis for finding the most relevant influential markets, investigations of the effect of time cycles on the target market and the discovery of the optimal neural network architectures. Previous research on US stock markets and other international markets have shown that the neural network approach is one of most powerful techniques for predicting stock market behaviour. Neural networks are capable of capturing the non-linear stochastic and chaotic patterns in the stock market time series data. This study discovered that the relative return series of the Open, High, Low and Close prices of the target market, show 6-day cycles during the studied period of about 14 years. Multi-layer feedforward neural networks trained with a backpropagation algorithm were used for the experiments. Two major testing methods: testing with randomly selected test data and forward testing, were examined and compared. The best neural network developed in this study has achieved 87%, 81% 83% and 81% accuracy respectively in predicting the next-day direction of the relative return of the Open, High, Low and Close prices of the target market. The architecture of this network consists of 33 input features, one hidden layer with 3 neurons and 4 output neurons. The best input features set includes the relative returns from 1 to 6 days in the past of the Open, High, Low and Close prices of the target market, the day of the week, and the previous day’s relative return of the Close prices of the US S&P 500 Index, US Dow Jones Industrial Average Index, US Gold/Silver Index, and the US Oil Index.Doctor of Philosophy
24
Tilakaratne, Chandima. "Stock market predictions based on quantified intermarket influences." University of Ballarat, 2007. http://archimedes.ballarat.edu.au:8080/vital/access/HandleResolver/1959.17/15394.
Full textAbstract:
This research investigated the feasibility and capability of neural network-based approaches for predicting the direction of the Australian Stock market index (the target market). It includes several aspects: univariate feature selection from the historical time series of the target market, inter-market analysis for finding the most relevant influential markets, investigations of the effect of time cycles on the target market and the discovery of the optimal neural network architectures. Previous research on US stock markets and other international markets have shown that the neural network approach is one of most powerful techniques for predicting stock market behaviour. Neural networks are capable of capturing the non-linear stochastic and chaotic patterns in the stock market time series data. This study discovered that the relative return series of the Open, High, Low and Close prices of the target market, show 6-day cycles during the studied period of about 14 years. Multi-layer feedforward neural networks trained with a backpropagation algorithm were used for the experiments. Two major testing methods: testing with randomly selected test data and forward testing, were examined and compared. The best neural network developed in this study has achieved 87%, 81% 83% and 81% accuracy respectively in predicting the next-day direction of the relative return of the Open, High, Low and Close prices of the target market. The architecture of this network consists of 33 input features, one hidden layer with 3 neurons and 4 output neurons. The best input features set includes the relative returns from 1 to 6 days in the past of the Open, High, Low and Close prices of the target market, the day of the week, and the previous day’s relative return of the Close prices of the US S&P 500 Index, US Dow Jones Industrial Average Index, US Gold/Silver Index, and the US Oil Index.Doctor of Philosophy
25
Orság, Štěpán. "Využití umělé inteligence na kapitálových trzích ke snížení rizika obchodování." Master's thesis, Vysoké učení technické v Brně. Ústav soudního inženýrství, 2016. http://www.nusl.cz/ntk/nusl-241366.
Full textAbstract:
This thesis deals with the prediction of trading at financial markets and by using the prediction is trying to reduce the risks of entering at the market. The prediction has been work out by using of artificial intelligence. The artificial intelligence is in this thesis represented by neural networks witch model and predict market behavior. The thesis contains a description of the financial markets, exchange trading and its analysis, and artificial intelligence methods. The main part of this thesis is a model for prediction of prices of a particular instrument. This model was developed in MATLAB and should serve as a support for making business decisions. Its aim is to predict the direction and magnitude of movement the price level for the next trading day. The output of this model is processed using the platform MetaTrader 4. At the end are evaluated possible gains from this solution.
26
Aase, Kim-Georg. "Text Mining of News Articles for Stock Price Predictions." Thesis, Norges teknisk-naturvitenskapelige universitet, Institutt for datateknikk og informasjonsvitenskap, 2011. http://urn.kb.se/resolve?urn=urn:nbn:no:ntnu:diva-13573.
Full textAbstract:
This thesis investigates the prediction of possible stock price changes immediately after news article publications, by automatic analysis of these news articles. Some background information about financial trading theory and text mining is given in addition to an overview of earlier related research in the field of automatic analyzes of news articles for predicting future stock prices. In this thesis a system is designed and implemented to predict stock price trends for the time immediately after the publication of news articles. This system consists mainly of four components. The first component gathers news articles and stock prices automatically from internet. The second component prepares the news articles by sending them to some document preprocessing steps and finding relevant features before they are sent to a document representation process. The third component categorizes the news articles into predefined categories, and finally the fourth component applies appropriate trading strategies depending on the category of the news article. This system requires a labeled data set to train the categorization component. This data set is labeled automatically on the basis of the price trends directly after the news article publication. An additional label refining step using clustering is added in an attempt to improve the labels given by the basic method of labeling by price trends.The findings indicate that a categorization of news articles provides additional information that can be used to forecast stock price trends. Experiments showed that the label refining method greatly improves the performance of the system. It was also shown that the timing of when to start the price trends used to label the data sets had a significant impact on the results. Trading simulations performed with the systems managed to gain positive returns (profits) on most of its trades. Some of the methods also managed to give better results than what trades performed with the manually labeled data set did.
27
Kharratzadeh, Milad. "Weblog analysis for predicting correlations in stock price evolutions." Thesis, McGill University, 2012. http://digitool.Library.McGill.CA:80/R/?func=dbin-jump-full&object_id=110708.
Full textAbstract:
In this thesis, we use data extracted from many weblogs to identify the underlying relations of a set of companies in the Standard and Poor (S&P) 500 index. In order to do this, we define a pairwise similarity measure for the companies based on the weblog articles and then apply a graph clustering procedure. We show that it is possible to capture some interesting relations between the companies using this method. As an application of this clustering procedure, and motivated by the fact that many of the factors affecting stock market can be captured by our clustering, we propose a cluster-based portfolio-selection method which combines information from the weblog data and historical stock prices. Through simulation experiments, we show that our method performs better (in terms of risk measures) than cluster-based portfolio strategies based on the sectors of the companies or the historical stock prices. This suggests that the methodology has the potential to identify groups of companies whose stock prices are more likely to be correlated in the future.Dans cette thèse, nous utilisons des données extraites de nombreux weblogs pour identifier les relations sous-jacentes entre les entreprises de l'index Standard and Poor (S&P) 500. C'est dans ce but que nous définissons une mesure de similarité entre ces entreprises, basée sur les articles de weblogs puis utilisée pour une procédure de regroupement. Nous montrons que cette méthode permet de capturer des relations intéressantes entre les entreprises. Motivés par le fait que de nombreux facteurs qui régissent les marchés financiers sont capturés par notre modèle, nous proposons une méthode de sélection de portefeuille basée sur ces regroupements. Cette méthode combine les informations tirées des weblogs ainsi que l'historique des marchés financiers.A travers des simulations, nous montrons que notre méthode donne de meilleurs résultats (en terme de prise de risque) qu'une sélection de portefeuille basée uniquement sur les secteurs des entreprises ou sur l'historique de la Bourse. Ces résultats suggèrent que cette méthodologie a le potentiel d'identifier les regroupements d'entreprises dont les capitalisations boursières ont de fortes chances d'être corrélés.
28
Wang, Zhuowen. "Prediction of stock market prices using neural network techniques." Thesis, University of Ottawa (Canada), 2004. http://hdl.handle.net/10393/26802.
Full textAbstract:
Issuing stocks is the key method to raise money for corporations. Today, stocks have become the most important financial instruments. Currently, there are several methods by which one can predict financial markets, but none of them is quite accurate. After introducing same basic concepts and the history of stocks, this work continues to introduce some typical fundamental and technical analysis methods already developed by economists, and then presents a relatively new system to forecast the stack market using revised Back Propagation (BP) algorithms. The system exploits BP neural networks to help find the correlation between stock price and the affecting factors hidden behind the financial market. The topology is a typical three-layer neural network with one input layer, one hidden layer and one output layer. The supervised algorithms are the Feed-forward, Cascade-forward, and Elman BP. They are trained respectively by seven BP techniques: the Gradient Descent BP, the Gradient Descent With Momentum BP, the Gradient Descent With Adaptive Learning Rate BP, the Gradient Descent With Momentum & Adaptive Learning Rate BP, the Levenberg-Marquardt BP, the Broyden-Fletcher-Goldfarb-Shanno (BFGS) Quasi-Newton, and the Resilient Propagation (RPROP) BP. Data used to train and test the neural networks involve the Shanghai Stock Exchange Composite Index, and the Shenzhen Stock Exchange Component Index.
29
Kruger, Sarah Debora. "The prediction value of the price/earnings ratio for headline earnings per share, dividend yields and share returns." Thesis, Stellenbosch : Stellenbosch University, 2005. http://hdl.handle.net/10019.1/70304.
Full textAbstract:
Mini study project (MBA)--University of Stellenbosch, 2005.ENGLISH ABSTRACT: This mini study project aims to investigate the prediction value ofpricelearnings (pIE) ratios. The ability of investors to predict earnings growth is tested by examining the relationship between PIE ratios and excess earnings growth. The study further also investigates the relationship between PIE ratios and two other variables: share returns and dividend yields. The study design was based on that of two other studies: Fuller, Huberts and Levinson (1993) and Hamman, Jordaan and Smit (1995). These studies specifically tested the random walk theory of earnings. In this study all the companies were allocated to one of four PIE portfolios according to the magnitude of their PIE ratio. The relationship between PIE ratios and the dependent variables (earnings growth, share returns and dividend yields) was then analysed by comparing the medians of the dependent variables of the different quartiles (pIE portfolios). The investigation into the relation between PIE ratios and excess earnings growth indicated that companies with high PIE ratios tend to have higher excess earnings growth. The relationship, however, seemed to be more pronounced in the one year results than in the two and four year results. The share returns seemed to be randomly distributed and it was more difficult to identify the correlation with PIE ratios. For a two and four year period however, the lowest PIE quartile delivered the highest returns and the highest PIE quartile performed very poorly. Lastly it was found that companies with high PIE ratios had lower dividend yields and companies with lower PIE ratios had higher dividend yields. Even though some departures from randomness were observed when comparing the PIE quartiles, the variability of the dependant variables at individual stock level was high and indicated random distribution.
AFRIKAANSE OPSOMMING: Hierdie ministudieprojek het ten doelom die voorspellingvermoë van prys/verdienste (PN) verhoudings te ondersoek. Die vermoë van beleggers om winsgroei te voorspel word getoets deur die verwantskap tussen PN-verhoudings en surplus winsgroei te ondersoek. Verder ondersoek die studie ook die verwantskap tussen PN-verhoudings en twee verdere veranderlikes: aandeelopbrengste en dividendopbrengste. Die ontwerp van die studie is gebaseer op dié van twee ander studies: Fuller, Huberts en Levinson (1993) en Hamman, Jordaan en Smit (1995). Die twee studies het spesifiek die ewekansige verspreiding van winste ondersoek. Alle maatskappye in hierdie studie is geallokeer aan een van vier PN-protefeuljes volgens die vlak van hulle PNverhouding. Die verwantskap tussen PN-verhoudings en die afhanklike veranderlikes (winsgroei, aandeelopbrengste en dividendopbrengste) is dan ondersoek deur die mediane van die afhanklike veranderlikes van die verskillende PN-kwartiele (portefeuljes) te vergelyk. Die analise van die surplus winsgroei het aangedui dat maatskappye met hoë PNverhoudings geneig is om beter surplus winsgroei te toon. Die verwantskap blyk egter om duideliker te wees vir 'n eenjaar-periode as vir 'n tydperk van twee of vier jaar. Die aandeelopbrengste het 'n ewekansige verspreiding getoon en dit was moeilik om 'n verwantskap met die PN-verhoudings te identifiseer. Vir 'n twee en vier jaar periode het die laagste PN-kwartiel die hoogste aandeelopbrengs gelewer en die hoogste PNkwartiel het baie sleg presteer. Laastens is daar gevind dat maatskappye met hoë PN-verhoudings laer dividendopbrengste gelewer het en maatskappye met lae PN-verhoudings hoë dividendopbrengste. Alhoewel afwykings van ewekansigheid geïdentifiseer is met die vergelyking tussen kwartiele, was die variansie van die afhanklike veranderlikes op individuele aandelevlak hoog en het gedui op 'n ewekansige verspreiding.
30
Endress, Tobias. "Quality of stock price predictions in online communities : groups or individuals?" Thesis, University of Gloucestershire, 2017. http://eprints.glos.ac.uk/4674/.
Full textAbstract:
Group decision-making and equity predictions are topics that are interesting for academic research as well as for business purposes. Numerous studies have been conducted to assess the quality of forecasts by financial analysts, but in general these studies still show little evidence that it is possible to generate accurate predictions that in the long run create, after transaction costs, profits higher than the market average. This thesis investigates an alternative approach to traditional financial analysis. This approach is based on Internet group decision-making and follows the suggestion that a group decision is better than the decision of an individual. The research project follows a mixed-methods approach in the form of a sequential study with a field experiment. Different groups—consisting of lay people, but also financial professionals—were formed purposefully in different group designs to generate equity forecasts. The field experiment was conducted following an e- Delphi approach with online questionnaires, but also in-depth interviews with all participants. Data from financial analysts was used to compare the predictions from the groups with actual results of share prices. The data from the experiment suggests that there are different variables, in terms of the individual characteristics of the participants, which indicated significant impact on the quality of equity predictions. The predictions of some participants (e.g. “PID-S-plus” rated participants) are apparently of significantly higher accuracy. The findings from the study indicate that intuition plays a significant role in the decision-making process not only for lay people, but also for financial analysts and other financial professionals. However, there are observable differences in the intuitive decision-making of lay people and experts. While it was possible to observe that intuition is interpreted as “random guess” by poor predictors, it was found that good predictors base their intuition on several factors—even including fundamental and macroeconomic considerations. The findings of the experiments led to an explanatory model that is introduced as the ‘Deliberated Intuition’ Model. The model of deliberated intuition which is proposed here views prediction as a process of practice which will be different for each individual. The model proposes that a predictor will decide, consciously or semi-consciously, when they feel ready to rely on gut-feeling, or to undertake more analysis. Generally, it appears to contribute to a good prediction to think about the problem in different ways and with various techniques. The experiment indicated that (online-) groups are not per se better than individuals. The Deliberated Intuition Model might help to prepare better group settings and improve prediction quality. Apparently a combination of rational and intuitive techniques leads to the best prediction quality.
31
Tilakaratne, Chandima University of Ballarat. "A neural network approach for predicting the direction of the Australian stock market index." University of Ballarat, 2004. http://archimedes.ballarat.edu.au:8080/vital/access/HandleResolver/1959.17/12804.
Full textAbstract:
This research investigated the feasibility and capability of neural network-based approaches for predicting the direction of the Australian Stock market index (the target market). It includes several aspects: univariate feature selection from the historical time series of the target market, inter-market analysis for finding the most relevant influential markets, investigations of the effect of time cycles on the target market and the discovery of the optimal neural network architectures. Previous research on US stock markets and other international markets have shown that the neural network approach is one of most powerful techniques for predicting stock market behaviour. Neural networks are capable of capturing the non-linear stochastic and chaotic patterns in the stock market time series data. This study discovered that the relative return series of the Open, High, Low and Close prices of the target market, show 6-day cycles during the studied period of about 14 years. Multi-layer feedforward neural networks trained with a backpropagation algorithm were used for the experiments. Two major testing methods: testing with randomly selected test data and forward testing, were examined and compared. The best neural network developed in this study has achieved 87%, 81% 83% and 81% accuracy respectively in predicting the next-day direction of the relative return of the Open, High, Low and Close prices of the target market. The architecture of this network consists of 33 input features, one hidden layer with 3 neurons and 4 output neurons. The best input features set includes the relative returns from 1 to 6 days in the past of the Open, High, Low and Close prices of the target market, the day of the week, and the previous day’s relative return of the Close prices of the US S&P 500 Index, US Dow Jones Industrial Average Index, US Gold/Silver Index, and the US Oil Index.Master of Information Technology by Research
32
Tilakaratne, Chandima. "A neural network approach for predicting the direction of the Australian stock market index." Thesis, University of Ballarat, 2004. http://researchonline.federation.edu.au/vital/access/HandleResolver/1959.17/66591.
Full textAbstract:
This research investigated the feasibility and capability of neural network-based approaches for predicting the direction of the Australian Stock market index (the target market). It includes several aspects: univariate feature selection from the historical time series of the target market, inter-market analysis for finding the most relevant influential markets, investigations of the effect of time cycles on the target market and the discovery of the optimal neural network architectures. Previous research on US stock markets and other international markets have shown that the neural network approach is one of most powerful techniques for predicting stock market behaviour. Neural networks are capable of capturing the non-linear stochastic and chaotic patterns in the stock market time series data. This study discovered that the relative return series of the Open, High, Low and Close prices of the target market, show 6-day cycles during the studied period of about 14 years. Multi-layer feedforward neural networks trained with a backpropagation algorithm were used for the experiments. Two major testing methods: testing with randomly selected test data and forward testing, were examined and compared. The best neural network developed in this study has achieved 87%, 81% 83% and 81% accuracy respectively in predicting the next-day direction of the relative return of the Open, High, Low and Close prices of the target market. The architecture of this network consists of 33 input features, one hidden layer with 3 neurons and 4 output neurons. The best input features set includes the relative returns from 1 to 6 days in the past of the Open, High, Low and Close prices of the target market, the day of the week, and the previous day’s relative return of the Close prices of the US S&P 500 Index, US Dow Jones Industrial Average Index, US Gold/Silver Index, and the US Oil Index.Master of Information Technology by Research
33
Tilakaratne, Chandima. "A neural network approach for predicting the direction of the Australian stock market index." University of Ballarat, 2004. http://archimedes.ballarat.edu.au:8080/vital/access/HandleResolver/1959.17/15397.
Full textAbstract:
This research investigated the feasibility and capability of neural network-based approaches for predicting the direction of the Australian Stock market index (the target market). It includes several aspects: univariate feature selection from the historical time series of the target market, inter-market analysis for finding the most relevant influential markets, investigations of the effect of time cycles on the target market and the discovery of the optimal neural network architectures. Previous research on US stock markets and other international markets have shown that the neural network approach is one of most powerful techniques for predicting stock market behaviour. Neural networks are capable of capturing the non-linear stochastic and chaotic patterns in the stock market time series data. This study discovered that the relative return series of the Open, High, Low and Close prices of the target market, show 6-day cycles during the studied period of about 14 years. Multi-layer feedforward neural networks trained with a backpropagation algorithm were used for the experiments. Two major testing methods: testing with randomly selected test data and forward testing, were examined and compared. The best neural network developed in this study has achieved 87%, 81% 83% and 81% accuracy respectively in predicting the next-day direction of the relative return of the Open, High, Low and Close prices of the target market. The architecture of this network consists of 33 input features, one hidden layer with 3 neurons and 4 output neurons. The best input features set includes the relative returns from 1 to 6 days in the past of the Open, High, Low and Close prices of the target market, the day of the week, and the previous day’s relative return of the Close prices of the US S&P 500 Index, US Dow Jones Industrial Average Index, US Gold/Silver Index, and the US Oil Index.Master of Information Technology by Research
34
Bång, Filippa. "Intraday price prediction of Nordic stocks with limit order book data." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-279300.
Full textAbstract:
Predicting the direction of mid price changes could facilitate the decision of when in time an order should be placed on the market. The purpose of this thesis is to evaluate modelling approaches used to classify the direction of mid price changes in the limit order book on short term. Multi-layer perceptron and long short-term memory neural networks are evaluated with two sets of features derived from Nordic limit order book data. When classifying the direction of the mid price on Swedish stock data, an average accuracy score of 0.5 is achieved for multiple of the experiments, which is significant better than the accuracy achieved by the random classifier. However, a majority of the models are prone to consequently classify the price change to be stationary. The results show that including the order flow imbal- ance in the set of features does not improve the predictability of the models. Moreover, we are taking order flow imbalance into account for the mid price modelling. Linear regression is used to model the possible linear relation between the order flow imbalance and price change in the limit order book. Using the model to classify the price change direction results in an accuracy score of 0.36, a value close to the by chance accuracy.Att förutse riktningen av aktieprisförändringar i orderboken skulle kunna användas för att bestämma när i tiden orderplacering bör ske. Syftet med uppsatsen är att utvärdera modelleringsmetoder för prediktion av kortsiktiga prisförändringar i orderboken för nordisk aktiedata. Multi-layer perceptron och LSTM-nätverk (där LSTM står för long short-term memory) evalueras tillsammans med två uppsättningar features deriverade från orderboksdata. Vid klassificering av prisriktningen i orderboken, uppnås i genomsnitt en riktighet på 50 % för flera av experimenten. En majoritet av modellerna är dock benägna att konsekvent klassificera prisriktningen som oförändrat. LSTM- modellen är den modell som resulterar varierade prisriktningar. Att inkludera obalans i orderflöde som feature resulterar inte i en generell förbättring av förutsägbarheten hos modellerna. Huruvida priset i orderboken efter en trade har en linjär relation till obalansen i orderflödet före en trade testas med en linjär regression. Användning av den linjära modellen för att klassificera riktningen av prisförändringar baserat på orderflödet resulterar i en riktighet på 36 %.
35
Castoe, Minna. "Predicting Stock Market Price Direction with Uncertainty Using Quantile Regression Forest." Thesis, Uppsala universitet, Tillämpad matematik och statistik, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-426188.
Full text
36
Boushehri, Ali Ghodsi. "Applying fuzzy logic to stock price prediction." Thesis, 2000. http://spectrum.library.concordia.ca/1116/1/MQ54332.pdf.
Full textAbstract:
The major concern of this study is to develop a system that can predict future prices in the stock markets by taking samples of past prices. Stock markets are complex. Their dramatic movements, and unexpected booms and crashes, dull all traditional tools. This study attempts to resolve such complexity using the subtractive clustering based fuzzy system identification method, the Sugeno type reasoning mechanism, and candlestick chart analysis. Candlestick chart analysis shows that if a certain pattern of prices occurs in the market, then the stock price will increase or decrease. Inspired by the key information that candlestick analysis uses, this study assumes that everything impacting a market, from economic factors to politics, is distilled into market price. The model presented in this study elicits, from historical data price, some of the rules which govern the market, and shows that rules which are drawn from a particular stock are to some extent independent of that stock, and can be generalized and applied to other stocks regardless of specific time or industrial field. The experimental results of this study in the duration of 3 months reveals that the model can correctly predict the direction of the market with an average hit ratio of 87%. In addition to daily prediction, this model is also capable of predicting the open, high, low, and close prices of desired stock, weekly and monthly.
37
Guan-YILee and 李冠毅. "Toward stock price prediction using Deep Learning." Thesis, 2019. http://ndltd.ncl.edu.tw/handle/52kzef.
Full text
38
Chen, Yan-Ming, and 陳彥銘. "Development of Multiple Classifiers for Stock Price Prediction." Thesis, 2007. http://ndltd.ncl.edu.tw/handle/46868911887476918328.
Full textAbstract:
碩士國立中正大學
會計所
95
The technique of predicting of stock investment has been developed for many years. Advancement of computer technology allows many studies to use data mining techniques to predict stock price, like neural network, decision trees, etc. In order to build a better modal for stock price prediction, this study tries to construct different ‘homogenous’ multiple classifiers (for example, an ensemble of neural networks) and ‘heterogeneous’ multiple classifiers (for example, an ensemble of neural networks, decision trees and logistic regression) against single classifiers that earlier studies often used. In addition to compare prediction accuracy with single classifiers, this study further compares return of investment with each constructed models. This study uses financial and macro economic ratios as input variables, the return of stock price as output variables, and Taiwan electronic companies as the research samples. The period of study is from the second season of 2002 to the third season of 2006. Regarding the experimental results, several findings are as follows: 1. Neural networks provide higher prediction accuracy and returns of investment than the other single classifiers. 2. Multiple classifiers outperform other single classifiers in terms of prediction accuracy and returns of investment. 3. Heterogeneous multiple classifiers have slightly better performance than homogenous multiple classifiers in prediction. 4. However, the homogenous multiple classifiers using neural networks by majority voting perform the best in returns of investment. 5. There is no significant difference between voting and bagging in prediction accuracy, but the former has better returns of investment than the latter.
39
Lee, Chun-Yi, and 李俊逸. "Applying Recurrent Neural Networks to Stock Price Prediction." Thesis, 2019. http://ndltd.ncl.edu.tw/handle/7srsve.
Full textAbstract:
碩士國立政治大學
資訊管理學系
107
With the rapid growth of computing equipment in Moore's Law and the rapid development of computing devices, humans now have computers with faster speeds, which makes artificial intelligence rise again. The reason is that the branch of artificial intelligence — deep learning becomes dominant, and many people are working on how to implement deep learning skill on difficult questions and make contribution to human society. This study attempts to use one of the deep learning skills, RNN (Recurrent Neural Network) to make predictions about the stock market. The factors affecting the stock market are very many, including many indicators that have been widely used by fund managers, investment experts, or general investors. This study uses RNN (Recurrent Neural Network) as an architecture. Based on the transaction volume (liquidity) and market value, choose from Top 50 largest company, this research chooses Taiwan Semiconductor Manufacturing Company (2330.TW), Foxconn Technology Group (2317.TW), MediaTek Inc. (2454.TW), Largan Precision Co., Ltd (3008.TW) as predicting the target. Through the self-learning recurrent neural network (RNN), we use the LSTM model in order to make useful predictions. This study compares the influence on (1) Number of neurons (2) the number of hidden layers (3) For how long or how many months backwards are the excellent periods to forecast next month(4) Different standardization methods (5) Different indicators (financial statement indicators, technical analysis indicators, fundamental analysis indicators, stock market trading data, macroeconomics data) and do One-hot Encoding on months to see the seasonal influence on market and make predictions.
40
Ciou, Jian-Jhih, and 邱建智. "Stock price prediction based on univariate uncertain association rules." Thesis, 2014. http://ndltd.ncl.edu.tw/handle/q7b7mk.
Full text
41
LAI, CHUNG-YEN, and 賴忠彥. "Prediction of Stock Price using Support Vector Interval Regression." Thesis, 2017. http://ndltd.ncl.edu.tw/handle/btv4y8.
Full textAbstract:
碩士國立高雄應用科技大學
資訊管理研究所碩士班
105
In recent years, Investment and financial management has become a part of people's lives. However, in the field of investment and financial management has a lot of investments, Stock investment has been the main investment and financial management tools for most investors. But the stock market technology analysis is increasingly complex and Technical indicators was also increasing rapidly. Investors in the face of this situation, it has long been difficult to make a rational analysis. So, this study uses technical indicators to predict the stock price of Taiwan stock market, including Stochastics oscillator, Williams %R, Relative Strength Index ... and many more. Use the Support Vector Regression to establish a regression model to predict stock price movements, and according to the previous study of the proposed changes in the definition of insensitive interval, extended out Support vector regression machine with parametric insensitive model. Considering the date of April 28, 2017 Day Trading tax paid by half. Therefore, this study adds the concept of Interval regression to the former method, extended out Support Vector Interval Regression machine with parametric insensitive model. In this study, we found that the rate of parameterized insensitive interval support vector interval regression was better than that of the other two methods. It also indicated that the research method proposed by this study was the profit of investors in stock investment Ability to have some help.
42
Liou, Ke Yi, and 劉克一. "Genetic Design of Neural Networks on Stock Price Prediction." Thesis, 2001. http://ndltd.ncl.edu.tw/handle/01735470534224698719.
Full textAbstract:
碩士真理大學
管理科學研究所
89
This research discusses the use of genetic algorithms (GAs) to design neural networks for stock price prediction. Genetic algorithms evolve the weights for neural networks. The technical indicators of the stocks are used as neural network inputs to predict the stock should be buy or sold. The GAs usually use binary chromosomes for coding solutions. This research proposes using floating-point chromosomes to design neural networks using SUGAL, the SUnderland Genetic Algorithms Library. This coding provides schemata of the shortest defining length, one for each parameter, which prevents chromosomes from disruption by the processes of crossover and mutation. GAs are reinforcement learning techniques based on a trial-and-error, requiring heavy computation. A simulator is needed for the system. We use the C language to design the simulator, running on Windows 2000. The system is tested on MSCI Taiwan of stocks. This research reports experiments demonstrating that GAs are both effective and robust to design neural networks in stock price prediction problems.
43
Hsu, Hsiao-Lan, and 徐小嵐. "Combining Structured and Unstructured Data for Stock Price Prediction." Thesis, 2018. http://ndltd.ncl.edu.tw/handle/xgnwd6.
Full textAbstract:
碩士元智大學
資訊管理學系
106
With the advancement of internet, investors can immediately track the latest news of the stock market they invest in. Therefore, many factors may affect the stock price are worth exploring in depth. The most common way to predict stock price will rise or fall is through structured stock price related information. As many previous studies have found that financial texts can also cause stock price volatility and even helpful to predict stock prices, therefore, in this paper for the unstructured financial news data was adopted sentiment analysis method. In addition to using the positive and negative degrees given by the emotional dictionary, the value of the degree of ex-citement in the dictionary was also used to predict the next day stock price. However, because some of the news are not have emotion words, therefore, use the latent dirichlet allocation topic model approach marks the topic of the text and gives the word in the topic the appropriate emotional score, thereby expanding the new emotional word. Finally, by using the combination of stock price information, sentiment features of emotional dictionaries and extended sentiment features, the feature combinations that can minimize stock price prediction errors are obtained.
44
"Time Series Prediction for Stock Price and Opioid Incident Location." Master's thesis, 2019. http://hdl.handle.net/2286/R.I.54930.
Full textAbstract:
abstract: Time series forecasting is the prediction of future data after analyzing the past data for temporal trends. This work investigates two fields of time series forecasting in the form of Stock Data Prediction and the Opioid Incident Prediction. In this thesis, the Stock Data Prediction Problem investigates methods which could predict the trends in the NYSE and NASDAQ stock markets for ten different companies, nine of which are part of the Dow Jones Industrial Average (DJIA). A novel deep learning model which uses a Generative Adversarial Network (GAN) is used to predict future data and the results are compared with the existing regression techniques like Linear, Huber, and Ridge regression and neural network models such as Long-Short Term Memory (LSTMs) models.
In this thesis, the Opioid Incident Prediction Problem investigates methods which could predict the location of future opioid overdose incidences using the past opioid overdose incidences data. A similar deep learning model is used to predict the location of the future overdose incidences given the two datasets of the past incidences (Connecticut and Cincinnati Opioid incidence datasets) and compared with the existing neural network models such as Convolution LSTMs, Attention-based Convolution LSTMs, and Encoder-Decoder frameworks. Experimental results on the above-mentioned datasets for both the problems show the superiority of the proposed architectures over the standard statistical models.Dissertation/Thesis
Masters Thesis Computer Science 2019
45
LIU, CHUN-YU, and 劉峻宇. "Applying Technical Analysis and Neural Networks for Stock Price Prediction." Thesis, 2018. http://ndltd.ncl.edu.tw/handle/st87nz.
Full textAbstract:
碩士國立臺北大學
電機工程學系
106
The stock market forecasting is an important issue in financial engineering. An accurate forecasting system helps investors obtain high profit margin. With the development of technologies and the evolution of big data, the stock market investment will no longer be directly performed by the human; instead, intelligent investment will provide investors more accurate strategy analysis and more effective investment decisions. Therefore, this study proposed to combine the technical analysis pointers with the back propagation neural network. The technical analysis provided several useful functions such as stock price analysis, forecasting, and obtaining the key data in the stock price. We used the technical pointers instead of the raw data as the input variables of neural networks and verified if the pre-processing data can achieve more accurate stock price prediction. The technical analysis indicator package was written in the R language. The four major indexes of U.S stock market, Dow Jones Industrial Average, Philadelphia Semiconductor Index, Standard & Poor's 500 Index, NASDAQ Composite Index and sixteen listed companies serve as the sample data. Several kinds of pre-processing models were introduced. Through looking into the experimental results, the proposed package helped the neural networks achieve better performance. The proposed package passed a comprehensive R archive network (CRAN) check and made contribution to R in the field of stock data analysis.
46
Lin, Yu-ting, and 林玉庭. "A Hybrid SOM-SVM Method for Taiwan Stock Price fluctuation Prediction on Valuable Stocks." Thesis, 2007. http://ndltd.ncl.edu.tw/handle/76851508560666755543.
Full textAbstract:
碩士國立高雄第一科技大學
資訊管理所
95
The stock price movement prediction is crucial issue. In this paper, we try to use self-organizing map and support vector machine to build a prediction system. This study focuses on the valuable stocks of the Taiwan stock market. To train the prediction model, nine fiscal indices are used to as input variables. According to experiment results, the hybrid self-organizing map and support vector machine model obtains a high is prediction rate and it better than the single support vector machine model in prediction accuracy.
47
"Short-term stock price prediction based on limit order book dynamics." 2015. http://repository.lib.cuhk.edu.hk/en/item/cuhk-1291968.
Full textAbstract:
An, Yang.Thesis Ph.D. Chinese University of Hong Kong 2015.
Includes bibliographical references (leaves 72-78).
Abstracts also in Chinese.
Title from PDF title page (viewed on 08, December, 2016).
48
Lou, Yu-Mei, and 樓玉梅. "The Analysis and Prediction of Stock Price from Macro-Economic Factors." Thesis, 1996. http://ndltd.ncl.edu.tw/handle/97986705397463832497.
Full text
49
Liu, Chen-Hao, and 劉鎮豪. "Develop a Hybrid System for Stock Price and Trading Points Prediction." Thesis, 2007. http://ndltd.ncl.edu.tw/handle/60108440856334174320.
Full textAbstract:
博士元智大學
工業工程與管理學系
95
The stock market has become the main outlet for investment recently in the world. The futures indicator, investment foundations, foreign capitals are diverse choices for investors. Investors may earn more money form the stock market by adopting a good forecasting system. When considering the stock market forecasting problem, two main topics need to be focused: stock price prediction and trading point prediction. Many studies are focused on the first topic, stock price prediction; but few of them are focused on trading point prediction. Because trading points prediction is like a random walk. Many studies try to use pattern matching methods to forecast the future trends, but they only can do the long trend forecasting. In this thesis, an efficiently hybrid forecasting system will be developed for be a short trend forecaster in this study. The hybrid system concludes three parts: (1) data preprocessing, (2) evolutionary forecasting method, (3) final decision making. In the first part, stock screening, feature selection, and data clustering are the necessary procedures. In the second part, stock price prediction and trading point prediction are different research fields, dissimilar Soft Computing methods will be adopted. Takagi-Sugeno-Kang (TSK) model will be adopted to predict the stock price; Case Based Reasoning (CBR), Back-Propagation Network (BPN), and Piece-wise Linear Represent (PLR) will be used to judge the trading points. All forecasting models have a lot parameters need to be calibrated. Considering the different solution spaces and problem complexities, evolutionary algorithms will be adopted to find the best parameters in the forecasting models. In the last, the final trading decision will be generated to compare some recent studies with the same conditions. No matter which topic we selected, this hybrid system developed in this study performs better. In stock price prediction, the forecasting error is less than 0.05%; in trading points prediction, the rate of return is greater than 123% in those target stocks.
50
Lu, Kun-shen, and 盧坤伸. "Integrating Genetic Programming and Technical Analysis on Asian Stock Price Prediction." Thesis, 2002. http://ndltd.ncl.edu.tw/handle/47014416056091716766.
Full textAbstract:
碩士國立雲林科技大學
財務金融系
90
The stock market that changes rapidly has great effect on our lives. Traditional technical index has many kinds and therefore it is not easy to choose the proper one. In addition, people have different choice according to different background knowledge. Recently, the technology of artificial intelligence always has good performance in every domain. It also plays an important role in the prediction of finance. Genetic programming is run by computer modeling to reach the goal of evolution. We use genetic programming to learn technical trading rules of Asian stock price by daily prices from 1999 to 2000. The rule extracted from each period has great difference and changes rapidly with the stock price. After transaction costs, the trading rules we extracted earn excess returns over a simple buy-and-hold strategy.