Twitter data models for bank risk contagion

Abstract A very important and timely area of research in finance is systemic risk modelling, which concerns the estimation of the relationships between different financial institutions, with the aim of establishing which of them are more contagious/subject to contagion. The aim of this paper is to develop a systemic risk model which, differently from existing ones, employs not only the information contained in financial market prices, but also big data coming from financial tweets. From a methodological viewpoint, we propose a new framework, based on graphical Gaussian models, that can estimate systemic risks with stochastic network models based on two different sources: financial markets and financial tweets, and suggest a way to combine them, using a Bayesian approach. From an applied viewpoint, we present the first systemic risk model based on big data, and show that such a model can help predicting the default probability of a bank, conditionally on the others.

[1]  Christian Upper,et al.  Estimating Bilateral Exposures in the German Interbank Market: Is There a Danger of Contagion? , 2002, SSRN Electronic Journal.

[2]  T. Aste,et al.  Correlation based networks of equity returns sampled at different time horizons , 2007 .

[3]  T. Louis,et al.  Bayes and Empirical Bayes Methods for Data Analysis. , 1997 .

[4]  A. Lo,et al.  Econometric Measures of Connectedness and Systemic Risk in the Finance and Insurance Sectors , 2011 .

[5]  G. Sheldon,et al.  Interbank Lending and Systemic Risk: An Empirical Analysis for Switzerland , 1998 .

[6]  Julien Idier,et al.  How Useful is the Marginal Expected Shortfall for the Measurement of Systemic Exposure? A Practical Assessment , 2011, Social Science Research Network.

[7]  J. Friedman,et al.  New Insights and Faster Computations for the Graphical Lasso , 2011 .

[8]  Wolfgang Breymann,et al.  Hierarchical structures in financial markets : a "turbulent approach" to stochastic volatility , 1999 .

[9]  G. Casella.  An Introduction to Empirical Bayes Data Analysis , 1985 .

[10]  H. Varian,et al.  Predicting the Present with Google Trends , 2009 .

[11]  Mattia Montagna.  Systemic Risk in Modern Financial Systems , 2016 .

[12]  A. Dawid,et al.  Hyper Markov Laws in the Statistical Analysis of Decomposable Graphical Models , 1993 .

[13]  Ronen Feldman,et al.  Techniques and applications for sentiment analysis , 2013, CACM.

[14]  Michael Boss,et al.  Network topology of the interbank market , 2003, cond-mat/0309582.

[15]  J. N. R. Jeffers,et al.  Graphical Models in Applied Multivariate Statistics. , 1990 .

[16]  Paolo Giudici,et al.  Estimating bank default with generalised extreme value regression models , 2015, J. Oper. Res. Soc..

[17]  Paolo Giudici,et al.  How to measure the quality of financial tweets , 2016 .

[18]  Leibniz-Informationszentrum Wirtschaft,et al.  Estimating Bilateral Exposures in the German Interbank Market: Is there a Danger of Contagion? , 2002 .

[19]  Paolo Giudici,et al.  Bayesian data mining, with application to benchmarking and credit scoring , 2001 .

[20]  Guido Caldarelli,et al.  Web Search Queries Can Predict Stock Market Volumes , 2011, PloS one.

[21]  H. Varian,et al.  Predicting the Present with Google Trends , 2012 .

[22]  P. Green,et al.  Decomposable graphical Gaussian model determination , 1999 .

[23]  Philip H. Dybvig,et al.  Bank Runs, Deposit Insurance, and Liquidity , 1983, Journal of Political Economy.

[24]  K. Kaski,et al.  Clustering and information in correlation based financial networks , 2003, cond-mat/0312682.

[25]  Johan Bollen,et al.  Twitter mood predicts the stock market , 2010, J. Comput. Sci..

[26]  Bing Liu,et al.  Mining and summarizing customer reviews , 2004, KDD.

[27]  Bradley P. Carlin,et al.  BAYES AND EMPIRICAL BAYES METHODS FOR DATA ANALYSIS , 1996, Stat. Comput..

[28]  Paolo Giudici,et al.  Graphical Network Models for International Financial Flows , 2016 .