A novel measure is introduced to forecast financial crises, which can also be seen as a supplementary measure in systemic risk analysis. The indicator (the market rank indicator MRI) considers the relation between the largest singular value of a matrix of the return time series and its k smallest singular values. The rationale behind this is that, in times of market excitation and higher correlation, the vectors of the return time series become closer in the linear space containing them. The MRI is related to the notion of condition number, a measure of how close returns are; therefore, the MRI increases in periods of market tensions. The measure is applied to selected stock market indexes and tested em- pirically for its sensitivity as well as against alternative measures of systemic risk. The MRI could be of interest for both regulators and speculators due to its forecasting power. The empirical analysis underlines that the proposed methodology is particularly appealing to forecast market distress and it shows a clear superiority in terms of predictive capability with respect to other existing measures.

The market rank indicator to detect financial distress

FIGINI S.
;
MAGGI m.
2018-01-01

Abstract

A novel measure is introduced to forecast financial crises, which can also be seen as a supplementary measure in systemic risk analysis. The indicator (the market rank indicator MRI) considers the relation between the largest singular value of a matrix of the return time series and its k smallest singular values. The rationale behind this is that, in times of market excitation and higher correlation, the vectors of the return time series become closer in the linear space containing them. The MRI is related to the notion of condition number, a measure of how close returns are; therefore, the MRI increases in periods of market tensions. The measure is applied to selected stock market indexes and tested em- pirically for its sensitivity as well as against alternative measures of systemic risk. The MRI could be of interest for both regulators and speculators due to its forecasting power. The empirical analysis underlines that the proposed methodology is particularly appealing to forecast market distress and it shows a clear superiority in terms of predictive capability with respect to other existing measures.
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11571/1210454
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 8
  • ???jsp.display-item.citation.isi??? 4
social impact