10 Correlations, Hierarchies, Networks and Clustering
261
10.6.3 Risk Management
How much money a given portfolio can lose? in normal market conditions? in stressed
market conditions? in the presence of systemic risk?
To answer these questions, the use of clusters and networks can help. As presented
previously, the clustering hierarchy can be used to filter a correlation [139, 142]
or a tail dependence [40] matrix, which helps to measure the risk in normal and
stressed market conditions respectively. The systemic risk as defined by the Bank
for International Settlements is the risk that a failure of a participant to meet its
contractual obligations may in turn cause other participants to default, with the chain
reaction leading to broader financial difficulties. Networks seem thus a particularly
relevant tool to study this kind of risk.
• Study of systemic risk:
– In [57], authors assert that the diminution of regulation has removed barriers
between sectors and regions allowing bank to diversify their risk, but it also
increased the economic risk through increased interdependencies.
– The paper [78] is focused on energy derivative markets, and their market integration which can be seen as a necessary condition for the propagation of price
shocks. The MST is used to “identify the most probable and the shortest path
for the transmission of price shocks”.
– Authors in [12, 13] identify the set of indices possessing influence over the
Asian region, namely the Hong Kong, Singapore and South Korea ones. Authors
claim that the findings of their study can be utilized in effective systemic risk
management and for the selection of an optimally-diversified portfolio, resilient
to system-level shocks.
– Authors in [98] focus on the US housing market. According to the paper, “dramatic increases in the systemic risk are usually accompanied by regime shifts,
which provide a means of early detection of housing bubbles.” They find a sharp
increase in housing market correlations over the past decade, indicating that systemic market risk has also greatly increased; They observe that prices diffuse in
complex ways that do not require geographical clusters unlike worldwide stock
markets which exhibit clear geographical clustering [130].
– The paper [154] is focused on the shipping market. Authors explore the connections between the shipping market and the financial market: The shipping market
can provide efficient warning before market downturn. Alike many economic
systems which have been exhibiting an increase in the correlation between different market sectors, a factor that exacerbates the level of systemic risk, the three
major world shipping markets, (i) the new ship market, (ii) the second-hand ship
market, and (iii) the freight market, have experienced such an increase. Authors
show it using the MST, Granger causality analysis, and Brownian distance on
the prices of the real shipping market, and the stock prices of publicly-listed
shipping companies.
261
10.6.3 Risk Management
How much money a given portfolio can lose? in normal market conditions? in stressed
market conditions? in the presence of systemic risk?
To answer these questions, the use of clusters and networks can help. As presented
previously, the clustering hierarchy can be used to filter a correlation [139, 142]
or a tail dependence [40] matrix, which helps to measure the risk in normal and
stressed market conditions respectively. The systemic risk as defined by the Bank
for International Settlements is the risk that a failure of a participant to meet its
contractual obligations may in turn cause other participants to default, with the chain
reaction leading to broader financial difficulties. Networks seem thus a particularly
relevant tool to study this kind of risk.
• Study of systemic risk:
– In [57], authors assert that the diminution of regulation has removed barriers
between sectors and regions allowing bank to diversify their risk, but it also
increased the economic risk through increased interdependencies.
– The paper [78] is focused on energy derivative markets, and their market integration which can be seen as a necessary condition for the propagation of price
shocks. The MST is used to “identify the most probable and the shortest path
for the transmission of price shocks”.
– Authors in [12, 13] identify the set of indices possessing influence over the
Asian region, namely the Hong Kong, Singapore and South Korea ones. Authors
claim that the findings of their study can be utilized in effective systemic risk
management and for the selection of an optimally-diversified portfolio, resilient
to system-level shocks.
– Authors in [98] focus on the US housing market. According to the paper, “dramatic increases in the systemic risk are usually accompanied by regime shifts,
which provide a means of early detection of housing bubbles.” They find a sharp
increase in housing market correlations over the past decade, indicating that systemic market risk has also greatly increased; They observe that prices diffuse in
complex ways that do not require geographical clusters unlike worldwide stock
markets which exhibit clear geographical clustering [130].
– The paper [154] is focused on the shipping market. Authors explore the connections between the shipping market and the financial market: The shipping market
can provide efficient warning before market downturn. Alike many economic
systems which have been exhibiting an increase in the correlation between different market sectors, a factor that exacerbates the level of systemic risk, the three
major world shipping markets, (i) the new ship market, (ii) the second-hand ship
market, and (iii) the freight market, have experienced such an increase. Authors
show it using the MST, Granger causality analysis, and Brownian distance on
the prices of the real shipping market, and the stock prices of publicly-listed
shipping companies.