arXiv subjects

Tomaso Aste

Publications and source records attributed to Tomaso Aste.

At least 73 records · Page 4Linked to original sources

arXiv2016

The multiplex dependency structure of financial markets

We propose here a multiplex network approach to investigate simultaneously different types of dependency in complex data sets. In particular, we consider multiplex networks made of four layers corresponding respectively to linear, non-linear, tail, and partial correlations among a set of financial time series. We construct the sparse graph on each layer using a standard network filtering procedure, and we then analyse the structural properties of the obtained multiplex networks. The study of the time evolution of the multiplex constructed from financial data uncovers important changes in intrinsically multiplex properties of the network, and such changes are associated with periods of financial stress. We observe that some features are unique to the multiplex structure and would not be visible otherwise by the separate analysis of the single-layer networks corresponding to each dependency measure.

physics.soc-ph↗

arXiv2016

What does past correlation structure tell us about the future? An answer from network filtering

We discovered that past changes in the market correlation structure are significantly related with future changes in the market volatility. By using correlation-based information filtering networks we device a new tool for forecasting the market volatility changes. In particular, we introduce a new measure, the "correlation structure persistence", that quantifies the rate of change of the market dependence structure. This measure shows a deep interplay with changes in volatility and we demonstrate it can anticipate market risk variations. Notably, our method overcomes the curse of dimensionality that limits the applicability of traditional econometric tools to portfolios made of a large number of assets. We report on forecasting performances and statistical significance of this tool for two different equity datasets. We also identify an optimal region of parameters in terms of True Positive and False Positive trade-off, through a ROC curve analysis. We find that our forecasting method is robust and it outperforms predictors based on past volatility only. Moreover the temporal analysis indicates that our method is able to adapt to abrupt changes in the market, such as financial crises, more rapidly than methods based on past volatility.

q-fin.PM↗

arXiv2016

A nonlinear impact: evidences of causal effects of social media on market prices

Online social networks offer a new way to investigate financial markets' dynamics by enabling the large-scale analysis of investors' collective behavior. We provide empirical evidence that suggests social media and stock markets have a nonlinear causal relationship. We take advantage of an extensive data set composed of social media messages related to DJIA index components. By using information-theoretic measures to cope for possible nonlinear causal coupling between social media and stock markets systems, we point out stunning differences in the results with respect to linear coupling. Two main conclusions are drawn: First, social media significant causality on stocks' returns are purely nonlinear in most cases; Second, social media dominates the directional coupling with stock market, an effect not observable within linear modeling. Results also serve as empirical guidance on model adequacy in the investigation of sociotechnical and financial systems.

q-fin.ST↗

arXiv2015

Anomalous volatility scaling in high frequency financial data

Volatility of intra-day stock market indices computed at various time horizons exhibits a scaling behaviour that differs from what would be expected from fractional Brownian motion (fBm). We investigate this anomalous scaling by using empirical mode decomposition (EMD), a method which separates time series into a set of cyclical components at different time-scales. By applying the EMD to fBm, we retrieve a scaling law that relates the variance of the components to a power law of the oscillating period. In contrast, when analysing 22 different stock market indices, we observe deviations from the fBm and Brownian motion scaling behaviour. We discuss and quantify these deviations, associating them to the characteristics of financial markets, with larger deviations corresponding to less developed markets.

q-fin.CP↗

arXiv2015

Time-dependent scaling patterns in high frequency financial data

We measure the influence of different time-scales on the dynamics of financial market data. This is obtained by decomposing financial time series into simple oscillations associated with distinct time-scales. We propose two new time-varying measures: 1) an amplitude scaling exponent and 2) an entropy-like measure. We apply these measures to intraday, 30-second sampled prices of various stock indices. Our results reveal intraday trends where different time-horizons contribute with variable relative amplitudes over the course of the trading day. Our findings indicate that the time series we analysed have a non-stationary multifractal nature with predominantly persistent behaviour at the middle of the trading session and anti-persistent behaviour at the open and close. We demonstrate that these deviations are statistically significant and robust.

q-fin.ST↗

arXiv2015

Measuring multiscaling in financial time-series

We discuss the origin of multiscaling in financial time-series and investigate how to best quantify it. Our methodology consists in separating the different sources of measured multifractality by analysing the multi/uni-scaling behaviour of synthetic time-series with known properties. We use the results from the synthetic time-series to interpret the measure of multifractality of real log-returns time-series. The main finding is that the aggregation horizon of the returns can introduce a strong bias effect on the measure of multifractality. This effect can become especially important when returns distributions have power law tails with exponents in the range [2,5]. We discuss the right aggregation horizon to mitigate this bias.

q-fin.ST↗

arXiv2015

Twitter Sentiment Analysis: Lexicon Method, Machine Learning Method and Their Combination

This paper covers the two approaches for sentiment analysis: i) lexicon based method; ii) machine learning method. We describe several techniques to implement these approaches and discuss how they can be adopted for sentiment classification of Twitter messages. We present a comparative study of different lexicon combinations and show that enhancing sentiment lexicons with emoticons, abbreviations and social-media slang expressions increases the accuracy of lexicon-based classification for Twitter. We discuss the importance of feature generation and feature selection processes for machine learning sentiment classification. To quantify the performance of the main sentiment analysis methods over Twitter we run these algorithms on a benchmark Twitter dataset from the SemEval-2013 competition, task 2-B. The results show that machine learning method based on SVM and Naive Bayes classifiers outperforms the lexicon method. We present a new ensemble method that uses a lexicon based sentiment score as input feature for the machine learning approach. The combined method proved to produce more precise classifications. We also show that employing a cost-sensitive classifier for highly unbalanced datasets yields an improvement of sentiment classification performance up to 7%.

cs.CL↗

arXiv2015

Network Filtering for Big Data: Triangulated Maximally Filtered Graph

We propose a network-filtering method, the Triangulated Maximally Filtered Graph (TMFG), that provides an approximate solution to the Weighted Maximal Planar Graph problem. The underlying idea of TMFG consists in building a triangulation that maximizes a score function associated with the amount of information retained by the network. TMFG uses as weights any arbitrary similarity measure to arrange data into a meaningful network structure that can be used for clustering, community detection and modeling. The method is fast, adaptable and scalable to very large datasets, it allows online updating and learning as new data can be inserted and deleted with combinations of local and non-local moves. TMFG permits readjustments of the network in consequence of changes in the strength of the similarity measure. The method is based on local topological moves and can therefore take advantage of parallel and GPUs computing. We discuss how this network-filtering method can be used intuitively and efficiently for big data studies and its significance from an information-theoretic perspective.

cs.DS↗

arXiv2015

In Quest of Significance: Identifying Types of Twitter Sentiment Events that Predict Spikes in Sales

We study the power of Twitter events to predict consumer sales events by analysing sales for 75 companies from the retail sector and over 150 million tweets mentioning those companies along with their sentiment. We suggest an approach for events identification on Twitter extending existing methodologies of event study. We also propose a robust method for clustering Twitter events into different types based on their shape, which captures the varying dynamics of information propagation through the social network. We provide empirical evidence that through events differentiation based on their shape we can clearly identify types of Twitter events that have a more significant power to predict spikes in sales than the aggregated Twitter signal.

cs.SI↗

arXiv2015

Multi-scaling of wholesale electricity prices

We empirically analyze the most volatile component of the electricity price time series from two North-American wholesale electricity markets. We show that these time series exhibit fluctuations which are not described by a Brownian Motion, as they show multi-scaling, high Hurst exponents and sharp price movements. We use the generalized Hurst exponent (GHE, $H(q)$) to show that although these time-series have strong cyclical components, the fluctuations exhibit persistent behaviour, i.e., $H(q)>0.5$. We investigate the effectiveness of the GHE as a predictive tool in a simple linear forecasting model, and study the forecast error as a function of $H(q)$, with $q=1$ and $q=2$. Our results suggest that the GHE can be used as prediction tool for these time series when the Hurst exponent is dynamically evaluated on rolling time windows of size $\approx 50 - 100$ hours. These results are also compared to the case in which the cyclical components have been subtracted from the time series, showing the importance of cyclicality in the prediction power of the Hurst exponent.

q-fin.ST↗

arXiv2015

Twitter Sentiment Analysis Applied to Finance: A Case Study in the Retail Industry

This paper presents a financial analysis over Twitter sentiment analytics extracted from listed retail brands. We investigate whether there is statistically-significant information between the Twitter sentiment and volume, and stock returns and volatility. Traditional newswires are also considered as a proxy for the market sentiment for comparative purpose. The results suggest that social media is indeed a valuable source in the analysis of the financial dynamics in the retail sector even when compared to mainstream news such as the Wall Street Journal and Dow Jones Newswires.

cs.CY↗

arXiv2015

Cell theory for glass-forming materials and jamming matter, combining free volume and cooperative rearranging regions

We investigate the statistical mechanics of glass-forming materials and jamming matter by means of a geometrically driven approach based on a revised cell theory. By considering the system as constituted of jammed blocks of increasing sizes, we obtain a unified picture that describes accurately the whole process from low densities to limit densities at the glass/jamming transition. The approach retrieves many of the aspects of existing theories unifying them into a coherent framework. In particular, at low densities we find a free volume regime, based on local relaxation process, at intermediate densities a cooperative length sets in, where both local and cooperative relaxation process are present. At even higher densities the increasing cooperative length suppresses the local relaxation and only the cooperative relaxation survives characterized by the divergence of the cooperative length, as suggested by the random first order theory. Finally a relation between the cooperative length and the hyperuniform length is also suggested.

cond-mat.stat-mech↗

arXiv2015

Relation between Financial Market Structure and the Real Economy: Comparison between Clustering Methods

We quantify the amount of information filtered by different hierarchical clustering methods on correlations between stock returns comparing it with the underlying industrial activity structure. Specifically, we apply, for the first time to financial data, a novel hierarchical clustering approach, the Directed Bubble Hierarchical Tree and we compare it with other methods including the Linkage and k-medoids. In particular, by taking the industrial sector classification of stocks as a benchmark partition, we evaluate how the different methods retrieve this classification. The results show that the Directed Bubble Hierarchical Tree can outperform other methods, being able to retrieve more information with fewer clusters. Moreover, we show that the economic information is hidden at different levels of the hierarchical structures depending on the clustering method. The dynamical analysis on a rolling window also reveals that the different methods show different degrees of sensitivity to events affecting financial markets, like crises. These results can be of interest for all the applications of clustering methods to portfolio optimization and risk hedging.

q-fin.ST↗

arXiv2014

Risk diversification: a study of persistence with a filtered correlation-network approach

The evolution with time of the correlation structure of equity returns is studied by means of a filtered network approach investigating persistences and recurrences and their implications for risk diversification strategies. We build dynamically Planar Maximally Filtered Graphs from the correlation structure over a rolling window and we study the persistence of the associated Directed Bubble Hierarchical Tree (DBHT) clustering structure. We observe that the DBHT clustering structure is quite stable during the early 2000' becoming gradually less persistent before the unfolding of the 2007-2008 crisis. The correlation structure eventually recovers persistence in the aftermath of the crisis settling up a new phase, distinct from the pre-cysts structure, where the market structure is less related to industrial sector activity. Notably, we observe that - presently - the correlation structure is loosing again persistence indicating the building-up of another, different, phase. Such dynamical changes in persistence and their occurrence at the unfolding of financial crises rises concerns about the effectiveness of correlation-based portfolio management tools for risk diversification.

q-fin.PM↗

arXiv2014

Measures of Causality in Complex Datasets with application to financial data

This article investigates the causality structure of financial time series. We concentrate on three main approaches to measuring causality: linear Granger causality, kernel generalisations of Granger causality (based on ridge regression and the Hilbert--Schmidt norm of the cross-covariance operator) and transfer entropy, examining each method and comparing their theoretical properties, with special attention given to the ability to capture nonlinear causality. We also present the theoretical benefits of applying non-symmetrical measures rather than symmetrical measures of dependence. We apply the measures to a range of simulated and real data. The simulated data sets were generated with linear and several types of nonlinear dependence, using bivariate, as well as multivariate settings. An application to real-world financial data highlights the practical difficulties, as well as the potential of the methods. We use two real data sets: (1) U.S. inflation and one-month Libor; (2) S$\&$P data and exchange rates for the following currencies: AUDJPY, CADJPY, NZDJPY, AUDCHF, CADCHF, NZDCHF. Overall, we reach the conclusion that no single method can be recognised as the best in all circumstances, and each of the methods has its domain of best applicability. We also highlight areas for improvement and future research.

q-fin.CP↗

arXiv2014

Systemic Losses Due to Counter Party Risk in a Stylized Banking System

We report a study of a stylized banking cascade model investigating systemic risk caused by counter party failure using liabilities and assets to define banks' balance sheet. In our stylized system, banks can be in two states: normally operating or distressed and the state of a bank changes from normally operating to distressed whenever its liabilities are larger than the banks' assets. The banks are connected through an interbank lending network and, whenever a bank is distressed, its creditor cannot expect the loan from the distressed bank to be repaid, potentially becoming distressed themselves. We solve the problem analytically for a homogeneous system and test the robustness and generality of the results with simulations of more complex systems. We investigate the parameter space and the corresponding distribution of operating banks mapping the conditions under which the whole system is stable or unstable. This allows us to determine how financial stability of a banking system is influenced by regulatory decisions, such as leverage; we discuss the effect of central bank actions, such as quantitative easing and we determine the cost of rescuing a distressed banking system using re-capitalisation. Finally, we estimate the stability of the UK and US banking systems in the years 2007 and 2012 showing that both banking systems were more unstable in 2007 and connectedness on the interbank market partly caused the banking crisis.

q-fin.GN↗

arXiv2013

Dependency Structure and Scaling Properties of Financial Time Series Are Related

We report evidence of a deep interplay between cross-correlations hierarchical properties and multifractality of New York Stock Exchange daily stock returns. The degree of multifractality displayed by different stocks is found to be positively correlated to their depth in the hierarchy of cross-correlations. We propose a dynamical model that reproduces this observation along with an array of other empirical properties. The structure of this model is such that the hierarchical structure of heterogeneous risks plays a crucial role in the time evolution of the correlation matrix, providing an interpretation to the mechanism behind the interplay between cross-correlation and multifractality in financial markets, where the degree of multifractality of stocks is associated to their hierarchical positioning in the cross-correlation structure. Empirical observations reported in this paper present a new perspective towards the merging of univariate multi scaling and multivariate cross-correlation properties of financial time series.

q-fin.ST↗

arXiv2013

Graph theory enables drug repurposing. How a mathematical model can drive the discovery of hidden Mechanisms of Action

We introduced a methodology to efficiently exploit natural-language expressed biomedical knowledge for repurposing existing drugs towards diseases for which they were not initially intended. Leveraging on developments in Computational Linguistics and Graph Theory, a methodology is defined to build a graph representation of knowledge, which is automatically analysed to discover hidden relations between any drug and any disease: these relations are specific paths among the biomedical entities of the graph, representing possible Modes of Action for any given pharmacological compound. These paths are ranked according to their relevance, exploiting a measure induced by a stochastic process defined on the graph. Here we show, providing real-world examples, how the method successfully retrieves known pathophysiological Mode of Actions and finds new ones by meaningfully selecting and aggregating contributions from known bio-molecular interactions. Applications of this methodology are presented, and prove the efficacy of the method for selecting drugs as treatment options for rare diseases.

q-bio.QM↗