Processus de Lévy et leurs applications en finance / No English summary available.

A necessidade de antecipar e identificar variações de acontecimentos apontam para uma nova direção nos mercados de bolsa de valores e vem de encontro às análises das oscilações de preços de ativos financeiros. Esta necessidade leva a argumentar sobre novas alternativas na predição de séries temporais financeiras utilizando métodos de aprendizado de máquinas e vários modelos têm sido desenvolvidos para efetuar a análise e a previsão de dados de ativos financeiros. Este trabalho tem por objetivo propor o desenvolvimento de um modelo de previsão adaptativo baseado em um sistema SVR-wavelet híbrido, que integra modelos de wavelets e Support Vector Regression (SVR) na previsão de séries financeiras. O método consiste na utilização da Transformada de Wavelet Discreta (DWT) a fim de decompor dados de séries de ativos financeiros que são utilizados como variáveis de entrada do SVR com o objetivo de prever dados futuros de ativos financeiros. O modelo proposto é aplicado a um conjunto de ativos financeiros do tipo Foreign Exchange Market (FOREX), Mercado Global de Câmbio, obtidos a partir de uma base de conhecimento público. As séries são ajustadas gerando-se novas predições das séries originais, que são comparadas com outros modelos tradicionais tais como o modelo Autorregressivo Integrado de Médias Móveis (ARIMA), o modelo Autorregressivo Fracionário Integrado de Médias Móveis (ARFIMA), o modelo Autorregressivo Condicional com Heterocedasticidade Generalizado (GARCH) e o modelo SVR tradicional com Kernel. Além disso, realizam-se testes de normalidade e de raiz unitária para distribuição não linear, tal como testes de correlação, para constatar que as séries temporais FOREX são adequadas para a comprovação do modelo híbrido SVR-wavelet e posterior comparação com modelos tradicionais. Verifica-se também a aderência ao Expoente de Hurst por meio da estatística de Reescalonamento (R/S). / The necessity to anticipate and identify changes in events points to a new direction in the stock exchange market and reaches the analysis of the oscillations of prices of financial assets. This necessity leads to an argument about new alternatives in the prediction of financial time series using machine learning methods. Several models have been developed to perform the analysis and prediction of financial asset data. This thesis aims to propose the development of SVR-wavelet model, an adaptive and hybrid prediction model, which integrates wavelet models and Support Vector Regression (SVR), for prediction of Financial Time Series, particularly Foreign Exchange Market (FOREX), obtained from a public knowledge base. The method consists of using the Discrete Wavelets Transform (DWT) to decompose data from FOREX time series, that are used as SVR input variables to predict new data. The series are adjusted by generating new predictions of the original series, which are compared with other traditional models such as the Autoregressive Integrated Moving Average model (ARIMA), the Autoregressive Fractionally Integrated Moving Average model (ARFIMA), the Generalized Autoregressive Conditional Heteroskedasticity model (GARCH) and the traditional SVR model with Kernel. In addition, normality and unit root tests for non-linear distribution, and correlation tests, are performed to verify that the FOREX time series are adequate for the verification of SVR-wavelet hybrid model and comparison with traditional models. There is also the adherence to the Hurst Exponent through the statistical Rescaled Range (R/S).

The aim of this graduation thesis is the descriptiton of R/S analysis and it's aplication on chosen time series of share prices and exchange rates. Some main models of financial time series will be mentioned in the second chapter. There will described basic linear models of stationary and non stationary time series and models of volatility. Then we will focus on the main theme of this thesis, R/S analysis. The algorithm of R/S analysis and the interpretation of the Hurst exponent will be described in the forth chapter. In the fifth chapter, the R/S analysis will by applied on real data sets. There will be two data sest of share prices of Telefónica O2 and Philip Morris and two data sets of exchange rates CZK/EUR and CZK/USD. The results will be interpreted and compared.

In this work we will describe methods for modeling multivariate financial time series. We will concentrate on both modeling expected value by multi- variate Box-Jenkins processes and primarily on modeling conditional corre- lations and volatility. Our main object will be DCC (Dynamic Conditional Correlation) model, estimation of its parameters and some other general- izations. Then we will programme DCC model in statistical software R and apply on real data. In applications we will concentrate on problem of high dimension of financial time series and on modeling conditional correlations data with outliers.

Topic of this master thesis is to examine whether weather related mood changes are in correlation with price of stocks. Thesis focuses on middle Europe stock market indexes PX, SAX, ATX and DAX. Research is based on relationship between daily cloud cover and development of the indexes form 1995 to 2012. It also focuses on comparison of several different models, especially models of seemingly unrelated regressions. It shows that indexes PX and ATX are significantly negatively correlated with local cloud cover. Use of seemingly unrelated regressions offers slightly better results. The relation between cloud cover and stock indexes is not strong enough to be used for weather based speculations

This thesis proposes a novel directed hypergraph based model for any database. We introduce the notion of association rules for multi-valued attributes, which is an adaptation of the definition of quantitative association rules known in the literature. The association rules for multi-valued attributes are integrated in building the directed hypergraph model. This model allows to capture attribute-level associations and their strength. Basing on this model, we provide association-based similarity notions between any two attributes and present a method for finding clusters of similar attributes. We then propose algorithms to identify a subset of attributes known as a leading indicator that influences the values of almost all other attributes. Finally, we present an association-based classifier that can be used to predict values of attributes. We demonstrate the effectiveness of our proposed model, notions, algorithms, and classifier through experiments on a financial time-series data set (S&P 500).

Title: Selected problems of financial time series modelling Author: Radek Hendrych Department: Department of Probability and Mathematical Statistics (DPMS) Supervisor: Prof. RNDr. Tomáš Cipra, DrSc., DPMS Abstract: The present dissertation thesis deals with selected problems of financial time series analysis. In particular, it focuses on two fundamental aspects of condi- tional heteroscedasticity modelling. The first part of the thesis introduces and discusses self-weighted recursive estimation algorithms for several classic univariate conditional heteroscedasticity models, namely for the ARCH, GARCH, RiskMetrics EWMA, and GJR-GARCH processes. Their numerical capabilities are demonstrated by Monte Carlo experiments and real data examples. The second part of the thesis proposes a novel approach to conditional covariance (correlation) modelling. The suggested modelling technique has been inspired by the essential idea of the multivariate orthogonal GARCH method. It is based on a suitable type of linear time-varying orthogonal transformation, which enables to employ the constant conditional correlation scheme. The correspond- ing model is implemented by using a nonlinear discrete-time state space representation. The proposed approach is compared with other commonly applied models. It demon- strates its...

Submitted by (ana.araujo@ufrpe.br) on 2016-08-09T12:21:50Z No. of bitstreams: 1 Neilson Ferreira de Lima.pdf: 1092223 bytes, checksum: aaf48f9e8f81c6deda5f9824c6e64b8a (MD5) / Made available in DSpace on 2016-08-09T12:21:50Z (GMT). No. of bitstreams: 1 Neilson Ferreira de Lima.pdf: 1092223 bytes, checksum: aaf48f9e8f81c6deda5f9824c6e64b8a (MD5) Previous issue date: 2012-09-10 / Conselho Nacional de Pesquisa e Desenvolvimento Científico e Tecnológico - CNPq / A time series is any set or ordered sequence of observations from a specific index, most often this is the time index, but may also be function of some physical parameter such as volume or space, among others. In our analysis, we observed indices financial markets, taking into account the number of return normalized by the standard deviation of the return series. And so we analyze the performance of five financial market indices. To model these markets we use the exponential distribution probability function is shown in the probability of an agent survive on the market without incurring a collision or shock. Generally, the analysis of financial time series is based on return series of stock, assets or indices. This series builds on successive differences between different times. Thus, it is used to measure the gains and losses over a given period. It can be captured price movement of a particular stock or index. And the volatility of these markets, we can classify it as a market "hot" markets, high volatility, market or "cold" low volatility. / Uma série temporal é qualquer conjunto ou sequência de observações ordenada a partir de um determinado índice, na maioria das vezes este índice é o tempo, mas poderá também ser função de algum parâmetro físico, como volume ou espaço, entre outros. Na nossa análise, observamos os índices de mercados financeiros; levando em conta a série de retorno normalizada pelo desvio padrão da série de retorno. E assim analisamos o comportamento de cinco índices de mercado financeiros. Para modelar estes mercados usamos a distribuição exponencial de probabilidade, está função nos mostra a probabilidade de um agente sobreviver no mercado sem sofrer colisão ou choques. Geralmente, a análise de séries temporais financeiras é feita com base na série de retornos de ações, ativos ou índices. Tal série toma como base sucessivas diferenças entre tempos distintos. Dessa forma, ela é usada para medir as perdas e ganhos ao longo de um determinado período. Nela pode ser capturado o movimento dos preços de uma determinada ação ou índice. E pela volatilidade destes mercados, podemos classifica-lo como mercado “quente”, mercados de alta volatilidade, ou mercado “frio”, de baixa volatilidade.

This diploma thesis focuses on modeling volatility in financial time series. The main approach to modelling volatility is using GARCH models which can capture the variability of conditional volatility of time series. For modelling a conditional mean value in time series are used ARMA models. In the series there are usually not fulfilled the assumption of earnings normality, therefore, are the earnings in most cased characterized by the leptokurtic shape of distribution. The thesis introduces some more distribution types, which can be more easily used for the earnings distribution - above all the Students t distribution. The aim of the thesis in the first part is to present the topic of financial time series and description of the GARCH models including their further modification. There are used e.g. IGARCH or other models capturing asymmetric impact of shocks such as GJR-GARCH. The second part deals with generated data, where are more in detail explored the volatility models and their behavior in corresponding financial time series. The third part focuses on the volatility estimation and forecasting for the financial time series. Firstly this concerns development of stock index MICEX secondly currency pair Russian Ruble to Czech Crown and eventually price development of the Brent crude oil. The goal of the third part is to present the impacts on volatility of chosen time series applied on the example of economic sanctions against Russia after annexation of the Crimea peninsula which happened in the first quarter 2014.

The stock market is a place in which numerous entities interact, operate, andchange state based on the decisions they make. Further, the stock market itselfevolves and changes its dynamics over time as a consequence of the individualactions taking place in it. In this sense, the stock market can be viewed andtreated as a complex adaptive system. In this study, an agent-based model,simulating the trading of a single asset has been constructed with the purposeof investigating how the collective behaviour affects the dynamics of the stockmarket. For this purpose, the agent-based modelling program NetLogo wasused. Lastly, the conclusion of the study revealed that the dynamics of thestock market are clearly dependent on some specific factors of the collectivebehaviour, such as the information source of the investors.