期刊名称：Documents de Travail du Centre d'Economie de la Sorbonne
印刷版ISSN：1955-611X
出版年度：2017
出版社：Centre d'Economie de la Sorbonne
摘要：The aim of this work is to create systematic trading strategies built upon several financialcrisis indicators based on the spectral properties of market dynamics. Within the limitationsof our framework and data, we will demonstrate that our systematic trading strategies areable to make money, not as a result of pure luck but, in a reproducible way and while avoidingthe pitfall of over fitting, as a result of the skill of the operators and their understanding andknowledge of the financial market. Using singular value decomposition (SVD) techniquesin order to compute all spectra in an efficient way, we have built two kinds of financialcrisis indicators with a demonstrable power of prediction. Firstly, there are those thatcompare at every date the distribution of the eigenvalues of a covariance or correlationmatrix to a distribution of reference representing either a calm or agitated market reference.Secondly, we have those that merely compute at every date a chosen spectral property (trace,spectral radius or Frobenius norm) of a covariance or correlation matrix. Aggregating thesignals provided by all the indicators in order to minimize false positive errors, we thenbuild systematic trading strategies based on a discrete set of rules governing the investmentdecisions of the investor. Finally, we compare our active strategies to a passive reference aswell as to random strategies in order to prove the usefulness of our approach and the addedvalue provided by the out-of-sample predictive power of the financial crisis indicators uponwhich our systematic trading strategies are built.
关键词：Prediction Methods; Financial Crisis; Financial Forecasting; Random Matrix Theory.
