Doctor of Philosophy / The motivation for the research presented in this thesis stems from the recent availability of high frequency limit order book data, relative scarcity of studies employing such data, economic significance of transaction costs management, and a perceived potential of data mining for uncovering patterns and relationships not identified by the traditional top-down modelling approach. We analyse and build computational models for order submissions on the Australian Stock Exchange, an order-driven market with a public electronic limit order book. The focus of the thesis is on the trade implementation problem faced by a trader who wants to transact a buy or sell order of a certain size. We use two approaches to build our models, top-down and bottom-up. The traditional, top-down approach is applied to develop an optimal order submission plan for an order which is too large to be traded immediately without a prohibitive price impact. We present an optimisation framework and some solutions for non-stationary and non-linear price impact and price impact risk. We find that our proposed transaction costs model produces fairly good forecasts of the variance of the execution shortfall. The second, bottom-up, or data mining, approach is employed for trade sign inference, where trade sign is defined as the side which initiates both a trade and the market order that triggered the trade. We are interested in an endogenous component of the order flow, as evidenced by the predictable relationship between trade sign and the variables used to infer it. We want to discover the rules which govern the trade sign, and establish a connection between them and two empirically observed regularities in market order submissions, competition for order execution and transaction cost minimisation. To achieve the above aims we first use exploratory analysis of trade and limit order book data. In particular, we conduct unsupervised clustering with the self-organising map technique. The visualisation of the transformed data reveals that buyer-initiated and seller-initiated trades form two distinct clusters. We then propose a local non-parametric trade sign inference model based on the k-nearest-neighbour classifier. The best k-nearest-neighbour classifier constructed by us requires only three predictor variables and achieves an average out-of-sample accuracy of 71.40% (SD=4.01%)1, across all of the tested stocks. The best set of predictor variables found for the non-parametric model is subsequently used to develop a piecewise linear trade sign model. That model proves superior to the k-nearest-neighbour classifier, and achieves an average out-of-sample classification accuracy of 74.38% (SD=4.25%). The result is statistically significant, after adjusting for multiple comparisons. The overall classification performance of the piecewise linear model indicates a strong dependence between trade sign and the three predictor variables, and provides evidence for the endogenous component in the order flow. Moreover, the rules for trade sign classification derived from the structure of the piecewise linear model reflect the two regularities observed in market order submissions, competition for order execution and transaction cost minimisation, and offer new insights into the relationship between them. The obtained results confirm the applicability and relevance of data mining for the analysis and modelling of stock market order submissions.

Thesis (Ph. D.)--University of Washington, 2006. / Vita. Includes bibliographical references (leaves 133-139).

O propósito dessa pesquisa é estudar a relação entre a revelação de informação corporativa e o comportamento de uma seleção de empresas com fortes políticas de revelação de informação e alto grau de capitalização do Mercado Acionário da Colômbia, para o ano 2014. Mediante esse estudo, é analisada a microestrutura utilizando informação de alta frequência e notícias corporativas publicadas na plataforma de Bloomberg Professional Services. A metodologia de análise para prover evidência da relação foi o estudo de eventos, testando a significância da diferença entre as médias e medianas pré-evento e pós-evento de alguns indicadores de liquidez, retorno e volatilidade. Os resultados permitem concluir que a disseminação de informação tem um impacto sobre a liquidez e a volatilidade do mercado. Percebe-se que no período posterior à publicação das notícias, o tamanho dos bid-ask spreads e a volatilidade do midquote diminui, os investidores negociam em média menores volumes e quantidade de operações e submetem menor quantidade de intenções de compra e venda. / The purpose of this investigation is to study the relationship between corporate disclosure and the behavior of a selection of companies, with strong disclosure policies and high market capitalization ratio of the Colombian Stock Market, for the entire year 2014. The idea of this investigation is to analyze the market microstructure using high frequency data and corporate information publicized through the Bloomberg professional services platform. The estimation technique to provide evidence of the relationship is the event study, testing the significance of the difference between the pre-event and post-event average and median of some indicators of return, liquidity and volatility. The results prove that the disemintation of information impact the market liquidity and volatility. It is noticed that in the post-event window, bid-ask spreads and volatility of the midquote decreases, traders negociate on average lower volums and number of transactions and submit fewer buy and sell order intentions.

Esta dissertação tem o objetivo de analisar a importância do Novo Mercado da BM&FBOVESPA para o desenvolvimento do mercado de capitais brasileiro. O Novo Mercado é um segmento especial de empresas listadas na bolsa de valores que adotam boas práticas de Governança Corporativa em sua gestão. Aderindo a tais práticas, as empresas assumem compromissos de informação e transparência adicionais aos existentes na legislação, favorecendo o monitoramento das companhias pelo mercado e oferecendo maior proteção aos acionistas e credores. Dessa forma, a Governança Corporativa facilita o acesso das empresas aos mercados financeiros e de capitais para financiar suas atividades e auxilia na redução dos riscos das operações. Adicionalmente, minimiza os problemas de informação assimétrica existentes nos mercados financeiros e de capitais, melhorando sua eficiência. A partir da implementação do Novo Mercado, em dezembro de 2000, o mercado de capitais brasileiro vem passando por mudanças significativas. Cresceu em volume de negócios, liquidez e valorização das ações. Aumentou significativamente o número de empresas que vem se utilizando do mercado de capitais para captar recursos e financiar seus projetos e atividades através de emissões de ações em bolsa, com destaque para as adesões das novas empresas ao Novo Mercado da bolsa. Nesse contexto, este estudo aborda em que medida o Novo Mercado da BM&FBOVESPA vem contribuindo para o processo de desenvolvimento recente do mercado de capitais nacional. / This dissertation aims at analyzing the importance of the Novo Mercado at BM&FBOVESPA for the development of the Brazilian stock market. Novo Mercado is a special segment of the companies listed in the stock market that adopted good practices of Corporate Governance in their management. By adopting these practices, the companies accept additional commitment about information and transparency to the existing ones in the legislation, favoring the monitoring of the market over the companies and offering more protection to the shareholders and creditors. Thus the Corporate Governance facilitates the access to the financial and capital markets in order to finance their activities and help reduce the operation risks. Moreover, it reduces the problems about asymmetric information existent in the financial and stock markets, improving their efficiency. After the introduction of the Novo Mercado, on December 2000, the Brazilian capital market has changed significantly. The amount of business has increased - as well as liquidity. Stocks have gone up. There has been an increase in the number of companies using the capital market to raise money to finance their projects and activities through public stock offering. It is important to notice that new companies have adopted the Novo Mercado. In this context, this study looks into the contribution of the Novo Mercado of BM&FBOVESPA to the recent process of development of the national stock market.

Submitted by Joao Mendes (joao_mendes14@msn.com) on 2015-10-19T11:06:10Z No. of bitstreams: 1 JMendes_Thesis FGV(14Aug2015).pdf: 1007852 bytes, checksum: b388f2d8462fe2b91d4eed87ab68fbd5 (MD5) / Rejected by Ana Luiza Holme (ana.holme@fgv.br), reason: Prezado João, Segundo as normas da ABNT o titulo do trabalho não aparece em todas as paginas do trabalho somente na capa, lombada e folha de aprovação. Tirar também das paginas acima mencionadas a palavra "Title". Tirar também seu nome do rodapé do trabalho. Faltou a introdução. A numeração das paginas não pode ser em numeral romano e deve aparecer a partir da introdução, sendo contada a partir da capa. o agradecimento é antes do resumo. Ana Luiza Holme 3799-3492 on 2015-10-19T12:16:52Z (GMT) / Submitted by Joao Mendes (joao_mendes14@msn.com) on 2015-10-19T15:49:46Z No. of bitstreams: 1 JMendes_Thesis FGV(19OUT2015).pdf: 965643 bytes, checksum: f2221c6075ea24b3c800c2f507e8435a (MD5) / Approved for entry into archive by Ana Luiza Holme (ana.holme@fgv.br) on 2015-10-19T15:59:13Z (GMT) No. of bitstreams: 1 JMendes_Thesis FGV(19OUT2015).pdf: 965643 bytes, checksum: f2221c6075ea24b3c800c2f507e8435a (MD5) / Made available in DSpace on 2015-10-19T16:03:45Z (GMT). No. of bitstreams: 1 JMendes_Thesis FGV(19OUT2015).pdf: 965643 bytes, checksum: f2221c6075ea24b3c800c2f507e8435a (MD5) Previous issue date: 2015-09-24 / Este trabalho estuda se existe impacto na volatilidade dos mercados de ações em torno das eleições nacionais nos países da OCDE e nos países em Desenvolvimento. Ao mesmo tempo, pretende, através de variáveis explicativas, descobrir os fatores responsáveis por esse impacto. Foi descoberta evidência que o impacto das eleições na volatilidade dos mercados de ações é maior nos países em Desenvolvimento. Enquanto as eleições antecipadas, a mudança na orientação política e o tamanho da população foram os factores que explicaram o aumento da volatilidade nos países da OCDE, o nível democrático, número de partidos da coligação governamental e a idade dos mercados foram os factores explicativos para os países em Desenvolvimento. / This project studies whether there is impact in stock market volatility around national elections in OECD countries and Developing countries. At the same time, it pretends, through a set of explanatory variables, find the factors that are responsible for that impact. It was found evidence that the impact of elections in stock market volatility is bigger in Developing countries. While early elections, the change in political orientation and the size of population were the factors that explained the abnormal volatility in OECD countries, the level of democracy, the number of parties of the governmental coalition and the age of the stock markets were the ones for Developing countries.

This study examines how stock market returns and volatility responses to macroeconomic news announcements in US and Europe, and oil prices. Moreover, the market risk associated with these stock markets based on selected countries and regions is also analyzed here. In all chapters, the data is in a weekly time horizon and it covers 21 countries from different contents. In particular, Data covers three different time periods, i.e. full sample from 1/1/2000 to 12/31/2015, before the financial crisis, i.e. from 1/1/2000 to 9/27/2008 and after the financial crisis, i.e. from 10/11/2008 to 12/31/2015. Chapter 2 studies the impact of macroeconomic news announcements on stock markets in 21 countries using US and European countries macroeconomic news announcements. The first part investigates the impact of macroeconomic news announcements surprises in US and European Countries on stock markets returns in these countries. The second part analyzes the impact of macroeconomic news announcements in US and European Countries on stock markets volatility in these countries. Our results show that stock markets in selected countries react differently to macroeconomic news announcement in US and Europe. Chapter 3 study the interaction and volatility spillover between oil prices and stock markets returns and volatility in selected countries and regions. Oil prices are based on West Texas Intermediate (WTI). The analysis use VAR(1)-GARCH(1,1) model to capture the interdependence between stocks market and oil prices. The findings show that there is interdependence between stock markets and oil price changes in most selected countries and regions. Chapter 4 study the market risk in stock markets returns in selected countries and regions using IGARCH(1,1) and GARCH(1,1) to obtain the value at risk (VaR) and the expected shortfall (ES). The findings of chapter 4 show that market risk was high for most selected countries before the financial crisis and low after the financial crisis.

O propósito dessa pesquisa é estudar a relação entre a revelação de informação corporativa e o comportamento de uma seleção de empresas com fortes políticas de revelação de informação e alto grau de capitalização do Mercado Acionário da Colômbia, para o ano 2014. Mediante esse estudo, é analisada a microestrutura utilizando informação de alta frequência e notícias corporativas publicadas na plataforma de Bloomberg Professional Services. A metodologia de análise para prover evidência da relação foi o estudo de eventos, testando a significância da diferença entre as médias e medianas pré-evento e pós-evento de alguns indicadores de liquidez, retorno e volatilidade. Os resultados permitem concluir que a disseminação de informação tem um impacto sobre a liquidez e a volatilidade do mercado. Percebe-se que no período posterior à publicação das notícias, o tamanho dos bid-ask spreads e a volatilidade do midquote diminui, os investidores negociam em média menores volumes e quantidade de operações e submetem menor quantidade de intenções de compra e venda. / The purpose of this investigation is to study the relationship between corporate disclosure and the behavior of a selection of companies, with strong disclosure policies and high market capitalization ratio of the Colombian Stock Market, for the entire year 2014. The idea of this investigation is to analyze the market microstructure using high frequency data and corporate information publicized through the Bloomberg professional services platform. The estimation technique to provide evidence of the relationship is the event study, testing the significance of the difference between the pre-event and post-event average and median of some indicators of return, liquidity and volatility. The results prove that the disemintation of information impact the market liquidity and volatility. It is noticed that in the post-event window, bid-ask spreads and volatility of the midquote decreases, traders negociate on average lower volums and number of transactions and submit fewer buy and sell order intentions.

Made available in DSpace on 2014-06-11T19:26:16Z (GMT). No. of bitstreams: 0 Previous issue date: 2010-12-17Bitstream added on 2014-06-13T18:54:26Z : No. of bitstreams: 1 nervis_jj_me_bauru.pdf: 692937 bytes, checksum: a9ef52afbfe5a4ae6482213875cfd47d (MD5) / Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES) / Estudos que proporcionem conhecer de forma mais adequada o mercado de capitais brasileiro são uma necessidade para um país que a cada dia tem a sua importância no cenário internacional acentuada. Compreender a dinâmica das flutuações do mercado de ações é um desafio científico possibilitado, no Brasil, por dois aspectos importantes: disponibilidade de dados de alta frequencia sobre os preços praticados no mercado e a utilização de métodos computacionais. O objetivo dessa pesquisa é verificar e analisar os principais fatos estilizados observados em séries temporais financeiras: agrupamento de volatilidade, distribuições de probabilidade com caudas gordas e a presença de memória de longo alcance na série temporal dos retornos absolutos. Para isso, foram utilizadas e analisadas as cotações intraday de ações de dez companhias negociadas na Bolsa de Valores, Mercadorias e Futuros que correspondem juntas a uma participação de 52,1%, para a data de 01/09/2009, no Ìndice Bovespa. Verificou-se a existência de vários fatos estilizados em todas as ações da amostra, bem como se procedeu a caracterização desses comportamentos por meio de gráficos e medidas estatísticas / Studies that provide to know in a more suitable way the Brazilian money market are a necessity for a country that has its importance increased in the international scenery every day. Understanding the dynamics of the stock market fluctuation is a scientific challenge possible, in Brazil, because of two important aspects: availability of high frequency data on the prices practiced in the stock market and the use of computing methods. The objective of this survey is to verify and analyze the stylized facts observed in financial seasonal series: gathering of volatility, probability distribution with fat tails and the presence of high reaching memory in the seasonal series of abolute recurrence. For this, it was used and analyzed the intraday quotations over stocks of ten enterprises in the stock exchange, commodities and futures that correspond together to a participation of 52,1% to th data of 09/01/2009, in the Bovespa index. It was verified the existence os several stylized fact in all stock samples and how it was preceded the characterization of this behavior by graphic displays and statistical measures

Esta dissertação tem o objetivo de analisar a importância do Novo Mercado da BM&FBOVESPA para o desenvolvimento do mercado de capitais brasileiro. O Novo Mercado é um segmento especial de empresas listadas na bolsa de valores que adotam boas práticas de Governança Corporativa em sua gestão. Aderindo a tais práticas, as empresas assumem compromissos de informação e transparência adicionais aos existentes na legislação, favorecendo o monitoramento das companhias pelo mercado e oferecendo maior proteção aos acionistas e credores. Dessa forma, a Governança Corporativa facilita o acesso das empresas aos mercados financeiros e de capitais para financiar suas atividades e auxilia na redução dos riscos das operações. Adicionalmente, minimiza os problemas de informação assimétrica existentes nos mercados financeiros e de capitais, melhorando sua eficiência. A partir da implementação do Novo Mercado, em dezembro de 2000, o mercado de capitais brasileiro vem passando por mudanças significativas. Cresceu em volume de negócios, liquidez e valorização das ações. Aumentou significativamente o número de empresas que vem se utilizando do mercado de capitais para captar recursos e financiar seus projetos e atividades através de emissões de ações em bolsa, com destaque para as adesões das novas empresas ao Novo Mercado da bolsa. Nesse contexto, este estudo aborda em que medida o Novo Mercado da BM&FBOVESPA vem contribuindo para o processo de desenvolvimento recente do mercado de capitais nacional. / This dissertation aims at analyzing the importance of the Novo Mercado at BM&FBOVESPA for the development of the Brazilian stock market. Novo Mercado is a special segment of the companies listed in the stock market that adopted good practices of Corporate Governance in their management. By adopting these practices, the companies accept additional commitment about information and transparency to the existing ones in the legislation, favoring the monitoring of the market over the companies and offering more protection to the shareholders and creditors. Thus the Corporate Governance facilitates the access to the financial and capital markets in order to finance their activities and help reduce the operation risks. Moreover, it reduces the problems about asymmetric information existent in the financial and stock markets, improving their efficiency. After the introduction of the Novo Mercado, on December 2000, the Brazilian capital market has changed significantly. The amount of business has increased - as well as liquidity. Stocks have gone up. There has been an increase in the number of companies using the capital market to raise money to finance their projects and activities through public stock offering. It is important to notice that new companies have adopted the Novo Mercado. In this context, this study looks into the contribution of the Novo Mercado of BM&FBOVESPA to the recent process of development of the national stock market.

abstract: There have been extensive research in how news and twitter feeds can affect the outcome of a given stock. However, a majority of this research has studied the short term effects of sentiment with a given stock price. Within this research, I studied the long-term effects of a given stock price using fundamental analysis techniques. Within this research, I collected both sentiment data and fundamental data for Apple Inc., Microsoft Corp., and Peabody Energy Corp. Using a neural network algorithm, I found that sentiment does have an effect on the annual growth of these companies but the fundamentals are more relevant when determining overall growth. The stocks which show more consistent growth hold more importance on the previous year’s stock price but companies which have less consistency in their growth showed more reliance on the revenue growth and sentiment on the overall company and CEO. I discuss how I collected my research data and used a multi-layered perceptron to predict a threshold growth of a given stock. The threshold used for this particular research was 10%. I then showed the prediction of this threshold using my perceptron and afterwards, perform an f anova test on my choice of features. The results showed the fundamentals being the better predictor of stock information but fundamentals came in a close second in several cases, proving sentiment does hold an effect over long term growth. / Dissertation/Thesis / Masters Thesis Computer Science 2016