feed icon rss

Ihre E-Mail wurde erfolgreich gesendet. Bitte prüfen Sie Ihren Maileingang.

Leider ist ein Fehler beim E-Mail-Versand aufgetreten. Bitte versuchen Sie es erneut.

Vorgang fortführen?

Exportieren
Filter
  • HU Berlin  (41)
  • SRB Cottbus
  • Inst. Menschenrechte
  • Technikmuseum Berlin
  • Hertie School
  • UdK Berlin
  • Härdle, Wolfgang Karl  (41)
Medientyp
Sprache
Region
Bibliothek
  • HU Berlin  (41)
  • SRB Cottbus
  • Inst. Menschenrechte
  • Technikmuseum Berlin
  • Hertie School
  • +
Erscheinungszeitraum
  • 1
    Online-Ressource
    Online-Ressource
    Berlin : Humboldt-Universität zu Berlin, Wirtschaftswissenschaftliche Fakultät
    UID:
    edochu_18452_4994
    Umfang: 1 Online-Ressource (30 Seiten)
    ISSN: 1860-5664
    Serie: 2011,54
    Inhalt: Source extraction and dimensionality reduction are important in analyzing high dimensional and complex financial time series that are neither Gaussian distributed nor stationary. Independent component analysis (ICA) method can be used to factorize the data into a linear combination of independent compo- nents, so that the high dimensional problem is converted to a set of univariate ones. However conventional ICA methods implicitly assume stationarity or stochastic homogeneity of the analyzed time series, which leads to a low accu- racy of estimation in case of a changing stochastic structure. A time varying ICA (TVICA) is proposed here. The key idea is to allow the ICA filter to change over time, and to estimate it in so-called local homogeneous intervals. The question of how to identify these intervals is solved by the LCP (local change point) method. Compared to a static ICA, the dynamic TVICA pro- vides good performance both in simulation and real data analysis. The data example is concerned with independent signal processing and deals with a port- folio of highly traded stocks.
    Sprache: Englisch
    URL: Volltext  (kostenfrei)
    Bibliothek Standort Signatur Band/Heft/Jahr Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 2
    Online-Ressource
    Online-Ressource
    Berlin : Humboldt-Universität zu Berlin, Wirtschaftswissenschaftliche Fakultät
    UID:
    edochu_18452_5202
    Umfang: 1 Online-Ressource (29 Seiten)
    ISSN: 1860-5664
    Serie: 2014,63
    Inhalt: International trade has been playing an extremely significant role in China over the last 20 years. This paper is aimed at investigating and understanding the relationship between China’smacro-economy and oil price fromthis newperspective. We find strong evidence to suggest that the increase of China’s price level, resulting fromoil price shocks, is statistically less than that of its main trade partners’. This helps us to understand the confused empirical results estimated within the SVAR framework and sheds light on recent data. More specifically, as for the empirical results, we find China’s output level is positively correlated with the oil price, and oil price shocks slightly appreciate the RMB against the US dollar. Positive correlation between China’s output and oil price shocks presumably results from the drop in China’s relative price induced by oil price shocks, which is inclined to stimulate China’s goods and service exports. The slight appreciation of the RMB could be justified by the drop in China’s relative price, which is indicated by economic theory. Moreover, constructing a simple model, our new perspective also helps us to understand the recent fact that together with the dramatic surge of the world oil price, while the oil imports of the other major countries (especially the largest oil import country US) in the world steadily decline or remain stable, China’s oil imports, in contrast, have kept rising steeply since the year 2004.
    Sprache: Englisch
    URL: Volltext  (kostenfrei)
    Bibliothek Standort Signatur Band/Heft/Jahr Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 3
    Online-Ressource
    Online-Ressource
    Berlin : Humboldt-Universität zu Berlin, Wirtschaftswissenschaftliche Fakultät
    UID:
    edochu_18452_5292
    Umfang: 1 Online-Ressource (47 Seiten)
    ISSN: 1860-5664
    Serie: 2016,31
    Inhalt: The CRIX (CRyptocurrency IndeX) has been constructed based on approximately 30 cryptos and captures high coverage of available market capitalisation. The CRIX index family covers a range of cryptos based on different liquidity rules and various model selection criteria. Details of ECRIX (Exact CRIX), EFCRIX (Exact Full CRIX) and also intraday CRIX movements may be found on the webpage of hu.berlin/crix.
    Sprache: Englisch
    URL: Volltext  (kostenfrei)
    Bibliothek Standort Signatur Band/Heft/Jahr Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 4
    Online-Ressource
    Online-Ressource
    Berlin : Humboldt-Universität zu Berlin
    UID:
    edochu_18452_19398
    Umfang: 1 Online-Ressource (35 Seiten)
    Inhalt: The interdependence, dynamics and riskiness of financial institutions are the key features frequently tackled in financial econometrics. We propose a Tail Event driven Network Quantile Regression (TENQR) model which addresses these three aspects. More precisely, our framework captures the risk propagation and dynamics in terms of a quantile (or expectile) autoregression involving network effects quantified through an adjacency matrix. To reflect the nature and risk content of systemic risk, the construction of the adjacency matrix is suggested to include tail event covariates. The model is evaluated using the SIFIs (systemically important financial institutions) identified by the Financial Stability Board (FSB) as main players in the global financial system. The risk decomposition analysis of it identifies the systemic importance of SIFIs and thus provides measures for the required level of additional loss absorbency. It is discovered that the network effect, as a function of the tail probability, becomes more profound in stress situations and brings the various impacts to the SIFIs located in different geographic regions.
    Sprache: Englisch
    URL: Volltext  (kostenfrei)
    Bibliothek Standort Signatur Band/Heft/Jahr Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 5
    UID:
    edochu_18452_19105
    Umfang: 1 Online-Ressource (59 Seiten)
    Inhalt: Diese Arbeit präsentiert ein Faktor-Copula-Modell zur Quantifizierung von systemischen Risiko in Finanzinstituten. Diese Arbeit knüpft an aktuelle Forschung über Faktor-Copula-Modelle und Systemrisiko an. Die zugrunde liegenden Daten sind Aktienpreisrenditen der 28 systemrelevanten Finanzinstitute und ein gemeinsamer Faktor, welcher ein Portfolio darstellt, gewichtet nach der Größe der jeweiligen Bank. Betreffend des Ein-Faktor-Copula-Modells mit einer Verteilungsannahme, die asymmetrische und extreme Abhängigkeit ermöglicht, stellt diese Analyse eine gute Annäherung an die zugrunde liegenden Daten dar. Die Schätzmethode der Copula-Dichtefunktion ist mit einer numerischen Integrations- und Optimierungsmethode, der Gauss-Legendre-Quadraten-Methode durchgeführt, um eine Annäherung an das nicht-analystisch lösbare System zu unterbreiten. Die Schätzungen zu den regulären und extremen Abhängigkeitskoeffizienten basieren auf dem Faktor-Copula-Modell und einem nicht-parametrischen Ansatz. Beide Ergebnisse vom parametrischen und nicht-parametrischen Ansatz deuten auf eine höhere Abhängigkeit in Extremwerten zwischen den systemrelevanten Banken im Jahr 2015. Anschließend stellt die Arbeit anerkannte Risikomaße vor und vergleicht diese anhand ihrer Eignung zur Messung von systemischen Risiko. Der Fokus der ausgewählten Risikomaße liegt dabei auf dem Schätzen der Risikosensitivität der Banken zum Systemportfolio. Daher wird in diesem Model die Anfälligkeit der Banken bewertet und die Ergebnisse zeigen einen erneuten Anstieg der Risikosensitivität im Jahr 2015.
    Inhalt: This work proposes a factor copula model to quantify systemic risk in financial institutions. This framework connects to recently trending research on factor copula modeling and systemic risk measurement. The underlying data are equity returns of the 28 systemically important financial institutions and a common factor which is a portfolio being weighted by these SIFIs. Considering a one-factor copula model with distributional assumptions that enable asymmetric and tail dependence, this framework provides great fit to the underlying financial data. The estimation of the copula density expression is accomplished by the Gauss-Legendre quadratures, a numerical integration and optimization procedure to solve expressions without analytical solutions. Dependence measures and tail dependence coefficients are obtained based on the factor copula framework and on a nonparametric approach. Both tail dependence measures, though estimated by a parametric and a nonparametric approach, yield results implying a higher tail dependence among the SIFIs in 2015. Then, this work introduces recognized risk measures which become compared in their appropriateness in measuring systemic risk. The focus of the chosen risk measures is to estimates the risk exposure of the financial institutions to the financial system. Hence, the vulnerability of the individual banks is assessed and results indicate again increasing exposure in 2015.
    Anmerkung: Masterarbeit Humboldt-Universität zu Berlin 2017
    Sprache: Englisch
    URL: Volltext  (kostenfrei)
    Bibliothek Standort Signatur Band/Heft/Jahr Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 6
    Online-Ressource
    Online-Ressource
    Berlin : Humboldt-Universität zu Berlin
    UID:
    edochu_18452_19253
    Umfang: 1 Online-Ressource (32 Seiten)
    Inhalt: More and more data are observed in form of curves. Numerous applications in finance, neuroeconomics, demographics and also weather and climate analysis make it necessary to extract common patterns and prompt joint modelling of individual curve variation. Focus of such joint variation analysis has been on fluctuations around a mean curve, a statistical task that can be solved via functional PCA. In a variety of questions concerning the above applications one is more interested in the tail asking therefore for tail event curves (TEC) studies. With increasing dimension of curves and complexity of the covariates though one faces numerical problems and has to look into sparsity related issues. Here the idea of FActorisable Sparse Tail Event Curves (FASTEC) via multivariate asymmetric least squares regression (expectile regression) in a high-dimensional framework is proposed. Expectile regression captures the tail moments globally and the smooth loss function improves the convergence rate in the iterative estimation algorithm compared with quantile regression. The necessary penalization is done via the nuclear norm. Finite sample oracle properties of the estimator associated with asymmetric squared error loss and nuclear norm regularizer are studied formally in this paper. As an empirical illustration, the FASTEC technique is applied on fMRI data to see if individual’s risk perception can be recovered by brain activities. Results show that factor loadings over different tail levels can be employed to predict individual’s risk attitudes.
    Sprache: Englisch
    URL: Volltext  (kostenfrei)
    Bibliothek Standort Signatur Band/Heft/Jahr Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 7
    UID:
    edochu_18452_14755
    Umfang: 1 Online-Ressource (38 Seiten)
    Inhalt: Implied volatility can be considered as a function of strike level and time to maturity. As it is calculated from the actual trading options, it contains dynamic, multi-dimensional information of options, modelling the implied volatility is an interesting task for researchers. Dynamic semiparametric factor models (DSFM) are used to model the implied volatility surface. It employs semiparametric factor functions and time variate loadings to reduce the dimensions of the data. This master thesis applies joint analysis with the time variate factor loadings resulted from DSFM, in order to discuss the relationship between index options and stock options. The data of DAX index option and its liquid components stock options will be applied in analysis. The result of the joint analysis shows, that the index option has long term relationship with its stock options. It is unlikely to disperse the risk by trading the stock options under the same index.
    Anmerkung: Masterarbeit Humboldt-Universität zu Berlin, Wirtschaftswissenschaftliche Fakultät 2009
    Sprache: Englisch
    URL: Volltext  (kostenfrei)
    Bibliothek Standort Signatur Band/Heft/Jahr Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 8
    UID:
    edochu_18452_20012
    Umfang: 1 Online-Ressource (34 Seiten)
    Inhalt: Im Rahmen dieser Masterarbeit habe ich die verschiedenen Methoden und Modelle des Deep Learnings zur Klassifizierung von Musikgattungen erfoscht. Neben den klassischen Methoden basierend auf MFCC und Spektogrammen wurden ebenfalls die neusten Methoden der Deep Learning Forschung benutzt. Diese habe ich auf einen Audio-Datensatz von Google Research angewendet. Der Code für dieses Projekt wurde in der Programmiersprache Python geschrieben und auf Quantlet sowie GitHub veröffentlicht.
    Inhalt: I researched different preparation methods and models to classify musical genre of audio data. We began with classical preparation methods based on MFCCs and spectrograms and moved to methods on the cutting edge of deep learning such as attention-based RNNs and dilated convolutions. We utilized the Audioset dataset from Google Research and all of our code was written in the Python programming language. A copy of the code used in this project can be found on Quantlet and GitHub.
    Anmerkung: Access to the code for the project directly on GitHub at https://github.com/dhpollack/mgc , Masterarbeit Humboldt-Universität zu Berlin 2018
    Sprache: Englisch
    URL: Volltext  (kostenfrei)
    Bibliothek Standort Signatur Band/Heft/Jahr Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 9
    Online-Ressource
    Online-Ressource
    Berlin
    UID:
    edochu_18452_14679
    Umfang: 1 Online-Ressource (63 Seiten)
    Inhalt: In this thesis we propose a risk management methodology to high-dimensional financial portfolios. Instead of estimating the joint density of the portfolios in a high-dimensional space, we are encouraged by using the independent component analysis (ICA) to decompose the dependent risk factors to a linear transformation of independent components (ICs). The marginal density and the volatility process of each IC are estimated in a univariate dimension. Thereafter the joint densities and the dependence structures of the ICs and the original risk factors can be calculated using the statistical property of the independence and its linear transformation. We assume the marginal densities of ICs belong to the generalized hyperbolic (GH) distribution family since this family possesses semi-heavy tails and mimics the empirical distributions of the ICs appropriately. Further we implement a nonparametric adaptive methodology to estimate the local volatilities of ICs based on a homogeneity test. In order to check the reliability of the proposed methodology, we consider a portfolio in our study: a 2-dimensional exchange rates DEM/USD and GBP/USD with 4 different trading strategies. The empirical studies show that the performance of the VaR forecast using the proposed methodology is better than the popular Delta-Gamma-Normal model. All calculations and simulations are able to be recalculated with the software XploRe.
    Anmerkung: Masterarbeit Humboldt-Universität zu Berlin, Wirtschaftswissenschaftliche Fakultät 2005
    Sprache: Englisch
    URL: Volltext  (kostenfrei)
    Bibliothek Standort Signatur Band/Heft/Jahr Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 10
    UID:
    edochu_18452_19318
    Umfang: 1 Online-Ressource (57 Seiten)
    Inhalt: Als Nebenerscheinung der Digitalisierung entstehen täglich gewaltige Mengen unstrukturierter Daten. Unstrukturierte Daten umfassen Video-, Sprach-, Text- und Bilddaten, welche für Menschen leicht zu interpretieren sind, aber für Computer eine Herausforderung darstellen. In den letzten Jahren wurde viel geforscht, um Text- und Sentimentanalysen in finanziellen Entscheidungsprozesse miteinzubeziehen. Textbasierte Analysen befassen sich mit dem verbalen Teil von Sprache, aber in der menschlichen Interaktion von Angesicht zu Angesicht kann nonverbale Kommunikation eine gleichwichtige Rolle in der Nachrichtenvermittlung spielen. Deep Learning ist eine vielseitige Methode, die in verschiedenen Anwendungen Maschinen kognitive Fähigkeiten verleiht. Diese Arbeit beschreibt den Aufbau von Deep Convolutional Neural Networks, mit der Fähigkeit zur Emotionserkennung in menschlichen Gesichtern. Diese Ergebnisse werden genutzt, um Videos der regelmäßigen Pressekonferenz der Europäischen Zentralbank zwischen 2011 und 2017 zu analysieren. Aus diesem Verarbeitungsschritt resultieren Gefühlswerte für 70 Pressekonferenzen und mehr als 200,000 einzelne Bildern. Es wird untersucht, inwiefern Informationen aus nonverbaler Kommunikation, gemessen in Gefühlsäußerungen, sich auf Bewegungen des Euro Stoxx 50 Index niederschlagen. Dieser 'face value' wird verglichen mit dem Wert der verbalen Äußerungen aus Basis entsprechender Literatur. Die Verwendung von Pressekonferenzen als Quelle unstrukturierter Daten und die Übertragung von nonverbaler Kommunikation auf Aktienkursbewegungen sind, nach bestem Wissen, bisher unbearbeitete Themen in der Forschung.
    Inhalt: As a side effect of digitalization, a massive amount of unstructured data is generated every day. Unstructured data comprises video, speech, text, and image data, which are easy to interpret for humans - but can be challenging for computers. Financial research has been much engaged in recent history with decision-making based on textual or sentiment analysis. Textual analysis is based on the verbal part of communication, but in human interaction on a face-to-face level, nonverbal communication can play an equally important role in supporting a message. The interpretation of emotions in facial expressions is a major component of nonverbal communication. Deep learning is a versatile technique, that is used in numerous applications, providing somewhat cognitive capabilities for machines. This thesis describes how to build a deep convolutional neural network with the ability to detect emotions in faces. Different approaches in deep convolutional model designs are tested and evaluated. The results are then used to evaluate videos of the regular press conference of the European Central Bank between January 2011 and September 2017. This processing step results in emotional-scores of facial expressions from 70 press conferences and more than 200,000 single pictures. It is investigated whether information of nonverbal communication, measured in levels of emotional excitement, can be linked to the movements of the Euro Stoxx 50 index. This 'face value' is compared to the value of speech and accompanying research. Using image data from press conferences as source of unstructured data and transferring of nonverbal communication to stock markets are both topics that, to the best of found knowledge, have not yet been focused upon in research.
    Anmerkung: Masterarbeit Humboldt-Universität zu Berlin 2017
    Sprache: Englisch
    URL: Volltext  (kostenfrei)
    Bibliothek Standort Signatur Band/Heft/Jahr Verfügbarkeit
    BibTip Andere fanden auch interessant ...
Schließen ⊗
Diese Webseite nutzt Cookies und das Analyse-Tool Matomo. Weitere Informationen finden Sie auf den KOBV Seiten zum Datenschutz