arXiv subjects

Roy Cerqueti

Publications and source records attributed to Roy Cerqueti.

At least 37 records · Page 2Linked to original sources

arXiv2020

Systemic risk assessment through high order clustering coefficient

In this article we propose a novel measure of systemic risk in the context of financial networks. To this aim, we provide a definition of systemic risk which is based on the structure, developed at different levels, of clustered neighbours around the nodes of the network. The proposed measure incorporates the generalized concept of clustering coefficient of order $l$ of a node $i$ introduced in Cerqueti et al. (2018). Its properties are also explored in terms of systemic risk assessment. Empirical experiments on the time-varying global banking network show the effectiveness of the presented systemic risk measure and provide insights on how systemic risk has changed over the last years, also in the light of the recent financial crisis and the subsequent more stringent regulation for globally systemically important banks.

physics.soc-ph↗

arXiv2020

Words ranking and Hirsch index for identifying the core of the hapaxes in political texts

This paper deals with a quantitative analysis of the content of official political speeches. We study a set of about one thousand talks pronounced by the US Presidents, ranging from Washington to Trump. In particular, we search for the relevance of the rare words, i.e. those said only once in each speech -- the so-called hapaxes. We implement a rank-size procedure of Zipf-Mandelbrot type for discussing the hapaxes' frequencies regularity over the overall set of speeches. Starting from the obtained rank-size law, we define and detect the core of the hapaxes set by means of a procedure based on an Hirsch index variant. We discuss the resulting list of words in the light of the overall US Presidents' speeches. We further show that this core of hapaxes itself can be well fitted through a Zipf-Mandelbrot law and that contains elements producing deviations at the low ranks between scatter plots and fitted curve -- the so-called king and vice-roy effect. Some socio-political insights are derived from the obtained findings about the US Presidents messages.

cs.CL↗

arXiv2020

Skewed non-Gaussian GARCH models for cryptocurrencies volatility modelling

Recently, cryptocurrencies have attracted a growing interest from investors, practitioners and researchers. Nevertheless, few studies have focused on the predictability of them. In this paper we propose a new and comprehensive study about cryptocurrency market, evaluating the forecasting performance for three of the most important cryptocurrencies (Bitcoin, Ethereum and Litecoin) in terms of market capitalization. At this aim, we consider non-Gaussian GARCH volatility models, which form a class of stochastic recursive systems commonly adopted for financial predictions. Results show that the best specification and forecasting accuracy are achieved under the Skewed Generalized Error Distribution when Bitcoin/USD and Litecoin/USD exchange rates are considered, while the best performances are obtained for skewed Distribution in the case of Ethereum/USD exchange rate. The obtain findings state the effectiveness -- in terms of prediction performance -- of relaxing the normality assumption and considering skewed distributions.

q-fin.ST↗

arXiv2020

Stratified communities in complex business networks

This paper presents a new definition of the community structure of a network, which takes also into account how communities are stratified. In particular, we extend the standard concept of clustering coefficient and provide the local $l$-adjacency clustering coefficient of a node $i$. We define it as an opportunely weighted mean of the clustering coefficients of nodes which are at distance $l$ from $i$. The stratus of the community associated to node $i$ is identified by the distance $l$ from $i$, so that the standard clustering coefficient is a peculiar local $l$-adjacency clustering coefficient at stratus $l=0$. As the distance $l$ varies, the local $l$-adjacency clustering coefficient is then used to infer insights on the community structure of the entire network. Empirical experiments on special business networks are carried out. In particular, the analysis of air traffic networks validate the theoretical proposal and provide supporting arguments on its usefulness.

physics.soc-ph↗

arXiv2020

Segregation with Social Linkages: Evaluating Schelling's Model with Networked Individuals

This paper generalizes the original Schelling (1969, 1971a,b, 2006) model of racial and residential segregation to a context of variable externalities due to social linkages. In a setting in which individuals' utility function is a convex combination of a heuristic function a la Schelling, of the distance to friends, and of the cost of moving, the prediction of the original model gets attenuated: the segregation equilibria are not the unique solutions. While the cost of distance has a monotonic pro-status-quo effect, equivalent to that of models of migration and gravity models, if friends and neighbours are formed following independent processes the location of friends in space generates an externality that reinforces the initial configuration if the distance to friends is minimal, and if the degree of each agent is high. The effect on segregation equilibria crucially depends on the role played by network externalities.

econ.GN↗

arXiv2019

Influence measures in subnetworks using vertex centrality

This work deals with the issue of assessing the influence of a node in the entire network and in the subnetwork to which it belongs as well, adapting the classical idea of vertex centrality. We provide a general definition of relative vertex centrality measure with respect to the classical one, referred to the whole network. Specifically, we give a decomposition of the relative centrality measure by including also the relative influence of the single node with respect to a given subgraph containing it. The proposed measure of relative centrality is tested in the empirical networks generated by collecting assets of the $S\&P$ 100, focusing on two specific centrality indices: betweenness and eigenvector centrality. The analysis is performed in a time perspective, capturing the assets influence, with respect to the characteristics of the analysed measures, in both the entire network and the specific sectors to which the assets belong.

physics.soc-ph↗

arXiv2019

Constrained Monte Carlo Markov Chains on Graphs

This paper presents a novel theoretical Monte Carlo Markov chain procedure in the framework of graphs. It specifically deals with the construction of a Markov chain whose empirical distribution converges to a given reference one. The Markov chain is constrained over an underlying graph, so that states are viewed as vertices and the transition between two states can have positive probability only in presence of an edge connecting them. The analysis is carried out on the basis of the relationship between the support of the target distribution and the connectedness of the graph.

math.PR↗

arXiv2019

A joint text mining-rank size investigation of the rhetoric structures of the US Presidents' speeches

This work presents a text mining context and its use for a deep analysis of the messages delivered by the politicians. Specifically, we deal with an expert systems-based exploration of the rhetoric dynamics of a large collection of US Presidents' speeches, ranging from Washington to Trump. In particular, speeches are viewed as complex expert systems whose structures can be effectively analyzed through rank-size laws. The methodological contribution of the paper is twofold. First, we develop a text mining-based procedure for the construction of the dataset by using a web scraping routine on the Miller Center website -- the repository collecting the speeches. Second, we explore the implicit structure of the discourse data by implementing a rank-size procedure over the individual speeches, being the words of each speech ranked in terms of their frequencies. The scientific significance of the proposed combination of text-mining and rank-size approaches can be found in its flexibility and generality, which let it be reproducible to a wide set of expert systems and text mining contexts. The usefulness of the proposed method and the speech subsequent analysis is demonstrated by the findings themselves. Indeed, in terms of impact, it is worth noting that interesting conclusions of social, political and linguistic nature on how 45 United States Presidents, from April 30, 1789 till February 28, 2017 delivered political messages can be carried out. Indeed, the proposed analysis shows some remarkable regularities, not only inside a given speech, but also among different speeches. Moreover, under a purely methodological perspective, the presented contribution suggests possible ways of generating a linguistic decision-making algorithm.

cs.CL↗

arXiv2018

Measuring network resilience through connection patterns

Networks are at the core of modeling many engineering contexts, mainly in the case of infrastructures and communication systems. The resilience of a network, which is the property of the system capable of absorbing external shocks, is then of paramount relevance in the applications. This paper deals with this topic by advancing a theoretical proposal for measuring the resilience of a network. The proposal is based on the study of the shocks propagation along the patterns of connections among nodes. The theoretical model is tested on the real-world instances of two important airport systems in the US air traffic network; Illinois (including the hub of Chicago) and New York states (with JFK airport).

cs.SI↗

arXiv2018

Exploring how innovation strategies at time of crisis influence performance: a cluster analysis perspective

This paper analyzes the connection between innovation activities of companies -- implemented before crisis -- and their performance -- measured at time of crisis. The companies listed in the STAR Market Segment of the Italian Stock Exchange are analyzed. Innovation is measured through the level of investments in total tangible and intangible fixed assets in 2006-2007, while performance is captured through growth -- expressed by variations of sales, total assets and employees -- profitability -- through ROI or ROS -- and productivity -- through asset turnover or sales per employee in the period 2008-2010. The variables of interest are analyzed and compared through statistical techniques and by adopting cluster analysis. In particular, a Voronoi tessellation is also implemented in a varying centroids framework. In accord with a large part of the literature, we find that the behavior of the performance of the companies is not univocal when they innovate.

q-fin.ST↗

arXiv2018

Intriguing yet simple skewness - kurtosis relation in economic and demographic data distributions; pointing to preferential attachment processes

In this paper, we propose that relations between high order moments of data distributions, for example between the skewness (S) and kurtosis (K), allow to point to theoretical models with understandable structural parameters. The illustrative data concerns two cases: (i) the distribution of income taxes and (ii) that of inhabitants, after aggregation over each city in each province of Italy in 2011. Moreover, from the rank-size relationship, for either S or K, in both cases, it is shown that one obtains the parameters of the underlying (hypothetical) modeling distribution: in the present cases, the 2-parameter Beta function, - itself related to the Yule-Simon distribution function, whence suggesting a growth model based on the preferential attachment process.

stat.AP↗

arXiv2018

A new measure for community structures through indirect social connections

Based on an expert systems approach, the issue of community detection can be conceptualized as a clustering model for networks. Building upon this further, community structure can be measured through a clustering coefficient, which is generated from the number of existing triangles around the nodes over the number of triangles that can be hypothetically constructed. This paper provides a new definition of the clustering coefficient for weighted networks under a generalized definition of triangles. Specifically, a novel concept of triangles is introduced, based on the assumption that, should the aggregate weight of two arcs be strong enough, a link between the uncommon nodes can be induced. Beyond the intuitive meaning of such generalized triangles in the social context, we also explore the usefulness of them for gaining insights into the topological structure of the underlying network. Empirical experiments on the standard networks of 500 commercial US airports and on the nervous system of the Caenorhabditis elegans support the theoretical framework and allow a comparison between our proposal and the standard definition of clustering coefficient.

cs.SI↗

arXiv2018

Data on the annual aggregated income taxes of the Italian municipalities over the quinquennium 2007-2011

This dataset contains the annual aggregated income taxes of all the Italian municipalities over the years 2007-2011. Data are clustered over the Italian regions and provinces. The source of the data is the Italian Ministry of Economics and Finance. The administrative variations in Italy over the quinquennium have been taken into account. Data are useful to understand the economic structure of Italy at the microscopic level of municipalities. They can serve also for making comparisons between economical aspects and other features of the Italian cities.

q-fin.ST↗

arXiv2018

Investigating the configurations in cross-shareholding: a joint copula-entropy approach

--- the companies populating a Stock market, along with their connections, can be effectively modeled through a directed network, where the nodes represent the companies, and the links indicate the ownership. This paper deals with this theme and discusses the concentration of a market. A cross-shareholding matrix is considered, along with two key factors: the node out-degree distribution which represents the diversification of investments in terms of the number of involved companies, and the node in-degree distribution which reports the integration of a company due to the sales of its own shares to other companies. While diversification is widely explored in the literature, integration is most present in literature on contagions. This paper captures such quantities of interest in the two frameworks and studies the stochastic dependence of diversification and integration through a copula approach. We adopt entropies as measures for assessing the concentration in the market. The main question is to assess the dependence structure leading to a better description of the data or to market polarization (minimal entropy) or market fairness (maximal entropy). In so doing, we derive information on the way in which the in- and out-degrees should be connected in order to shape the market. The question is of interest to regulators bodies, as witnessed by specific alert threshold published on the US mergers guidelines for limiting the possibility of acquisitions and the prevalence of a single company on the market. Indeed, all countries and the EU have also rules or guidelines in order to limit concentrations, in a country or across borders, respectively. The calibration of copulas and model parameters on the basis of real data serves as an illustrative application of the theoretical proposal.

q-fin.ST↗

arXiv2018

SME investment best strategies. Outliers for assessing how to optimize performance

Any research on strategies for reaching business excellence aims at revealing the appropriate course of actions any executive should consider. Thus, discussions take place on how effective a performance measurement system can be estimated, or/and validated. Can one find an adequate measure (i) on the performance result due to whatever level of investment, and (ii) on the timing of such investments? We argue that extreme value statistics provide the answer. We demonstrate that the level and timing of investments allow to be forecasting small and medium size enterprises (SME) performance, - at financial crisis times. The "investment level" is taken as the yearly total tangible asset (TTA). The financial/economic performance indicators defining growth are the sales or total assets variations; profitability is defined from returns on investments or returns on sales. Companies on the Italian Stock Exchange STAR Market serve as example. It is found from the distributions extreme values that outlier companies (with positive performance) are those with the lowest but growing TTA. In contrast, the SME with low TTA, but which did not increase its TTA, before the crisis, became a negative outlier. The outcome of these statistical findings should suggest strategies to SME board members.

q-fin.GN↗

arXiv2018

G-games with coalitions

This paper models games where the strategies are nodes of a graph G (we denote them as G-games) and in presence of coalition structures. The cases of one-shot and repeated games are presented. In the latter situation, coalitions are assumed to move from a strategy to another one under the constraint that they are adjacent in the graph. We introduce novel concepts of pure and mixed equilibria which are comparable with classical Nash and Berge equilibria. A Folk Theorem for G-games of repeated type is presented. Moreover, equilibria are proven to be described through suitably defined Markov Chains, hence leading to a constrained Monte Carlo Markov Chain procedure.

math.PR↗

arXiv2017

Data science for assessing possible tax income manipulation: The case of Italy

This paper explores a real-world fundamental theme under a data science perspective. It specifically discusses whether fraud or manipulation can be observed in and from municipality income tax size distributions, through their aggregation from citizen fiscal reports. The study case pertains to official data obtained from the Italian Ministry of Economics and Finance over the period 2007-2011. All Italian (20) regions are considered. The considered data science approach concretizes in the adoption of the Benford first digit law as quantitative tool. Marked disparities are found, - for several regions, leading to unexpected "conclusions". The most eye browsing regions are not the expected ones according to classical imagination about Italy financial shadow matters.

q-fin.ST↗

arXiv2017

Earthquakes economic costs through rank-size laws

This paper is devoted to assess the presence of some regularities in the magnitudes of the earthquakes in Italy between January $24^{th}$, 2016 and January $24^{th}$, 2017, and to propose an earthquakes cost indicator. The considered data includes the catastrophic events in Amatrice and in Marche region. To our purpose, we implement two typologies of rank-size analysis: the classical Zipf-Mandelbrot law and the so-called universal law proposed by Cerqueti and Ausloos (2016). The proposed generic measure of the economic impact of earthquakes moves from the assumption of the existence of a cause-effect relation between earthquakes magnitudes and economic costs. At this aim, we hypothesize that such a relation can be formalized in a functional way to show how infrastructure resistance affects the cost. Results allow us to clarify the impact of an earthquake on the social context and might serve for strengthen the struggle against the dramatic outcomes of such natural phenomena.

physics.soc-ph↗