The geometry of the The geometry of the marketmarket
ContentsContents1 The Market Geometry
Market metricPrincipal directionsEffective dimensionsA measure of structureNew structure after 1997
2 Market networksNetworks in and outside crises
Connection intensities3 Market shape: precursor of endogeneous crisis and return to
normalityGeometrical volumeSkewness and kurtosis
The metric
((FromFrom thethe EuclideanEuclidean distancedistance ofof thethe timetime seriesseries))
dd
IBMIBM
GEGE
)1(2 ijij cd −= (Mantegna & Stanley, 1999)
))(log())(log()( 1 kpkpkr tt −−= p: pricer: return
Market space1. The N stock coordinates are computed from the
distances. Embedding space dimension = N-12. Find the center of mass R=Σ m(k) x(k) / Σ m(k)3. Find coordinates in the center of mass system
y(k) = x(k) - R4.4. ConstructConstruct thethe inertialinertial tensor tensor TTijij ==ΣΣ m(km(k) ) yyii(k(k) ) yyjj(k(k))5.5. FindFind thethe eigenvectorseigenvectors andand eigenvalueseigenvalues ofof T : (T : (λλii,e,eii))6.6. Compare Compare withwith thethe samesame constructionconstruction for for permutedpermuted
datadata
1 - The Market Geometry
What is the number of dimensions of the manifoldcontaining the systematic components of all stocks ?
S&P500 S&P500 andand DowDow JonesJones, , dailydaily datadata
35 stocks, 10 years 70 stocks, 10 years249 stocks, 33 years 253 stocks, 35 years253 stocks, 22 years 424 stocks, 10 years
InIn allall cases: cases: 6 dimensions are enough !
Geometria do Mercado Financeiro
TheThe systematicsystematic componentcomponentisis containedcontained inin f f dimensionsdimensions
OrderedOrdered andand normalizednormalized eigenvalueseigenvalues
λλ+(1+(1--λλ*)*)
λ : actualλ* : random
Geometria do Mercado FinanceiroEffective dimensions
0 10 20 300.2
0.3
0.4
0.5
0.6
0.7
0.8
0.9
11998-2008 424 Stocks
λ +
(1- λ
*)
0 10 20 300.2
0.3
0.4
0.5
0.6
0.7
0.8
0.9
1
λ +
(1- λ
*)
1988-2008 253 Stocks
Redes de Mercado
Shape changes in the market space
Shape and crises
-0.5
0
0.5
-0.5
0
0.5-0.5
0
0.5
Jul.1998 to Jul.2000
Uti IT Fin Heal Cons Ind Ene
“Spherical” marketTypical in all projections
for “surrogate data” or in “business-as-usual”
periods
During crises there isdistortion and reduction
of volume
Redes de MercadoShape and crises
-0.5
0
0.5-0.5
0
0.5
-0.5
0
0.5
Mar.1998 to Mar.2008
Uti IT Fin Heal Cons Ind Ene
-0.500.5
-0.500.5
-0.5
0
0.5
2001 253 stocks
e2
e3
-0.5 0 0.5-0.500.5
-0.5
0
0.5
e1
2007 253 stocks
e3
e2
-0.5 00.5
-0.500.5
-0.5
0
0.5
e1
1992 253 stocks
e3
e2
-0.50
0.5
-0.500.5
-0.5
0
0.5
e1
Surrogate Data 253 stocks
e3
e2
Geometria do Mercado FinanceiroA structure index
∑=
⎟⎟⎠
⎞⎜⎜⎝
⎛−=
6
11
)()('
i t
tt i
iSλλ
Structure index
After 1997 deviationsfrom sphericity become
more frequent.
What happened ?
λ : actualλ’: random
17/04/71 07/10/76 30/03/82 20/09/87 12/03/93 02/09/98 23/02/04 15/08/090
10
20
30
40
50230 stocks
S
88 89 90 91 92 93 94 95 96 97 98 99 00 01 02 03 04 05 06 07 080
5
10
15
20253 stocks A new regime after 1997
SS
>5
Redes de MercadoMarket networks
MarketMarket networksnetworks: : FromFrom a a fullyfully connectedconnectednetworknetwork to a to a sparsesparse oneone
1. minimal spanning tree2. LD6 = smallest distance in
R6 that guarantees the network connectivity
3. hierarchical clustering
02
12
,,6
,,6
6
6
=⇒>
=⇒≤
jiDji
jiDji
bL
d
bL
d
Aug2000
28
Energy
73
Industrial
114
Consumer
44
Health
70
Financial
56
Technology
39
Utilities
Few connections in normal periods
MarketMarket networksnetworks
The economic agentsare much more correlated duringmarket crises
Redes de MercadoMarket networks
Jan2008
28
Energy
73
Industrial
114
Consumer
44
Health
70
Financial
56
Technology
39
Utilities
An increased number of connections, mostly inside sectors
Redes de MercadoMarket networks
Sep2001
28
Energy
73
Industrial
114
Consumer
44
Health
70
Financial
56
Technology
39
Utilities
Redes de MercadoMarket networks
Another structure indexAnother structure index
Ratio of weak and
strong links
1997 1998 2000 2001 2002 2004 2005 2006 20080
0.5
1
1.5424 stocks From Jan.1998 to Mar.2008
R
1997 1998 2000 2001 2002 2004 2005 2006 2008
R>0
.5
∑
∑
>
≤=
66
66
),(
6
),(
6
),(
),(
Dt
Dt
Ljidt
Ljidt
tjid
jid
R
SynchronizationSynchronizationRedes de MercadoSynchronization
Sep2001
Uti IT Fin Heal Cons Ind Ene
Mar1998otherwises
Ljids
i
Dti
02
),(166
=
∃⇔= ≤
The state depends on the existence of a strong link inside or outside the sector
Redes de MercadoTopologiaSynchronization
Dec2007
Jan2008
Feb2008
Uti IT Fin Heal Cons Ind Ene
Aug2000
Sep2000
Redes de MercadoMarket shape as a precursor of crises and indicator of return to normality
-- CharacterizingCharacterizing shapeshape::-- Volume, Volume, asymmetryasymmetry andand tailstails-- MardiaMardia’’ss SkewnessSkewness KK33 andand KurtosisKurtosis KK44
-- TheThe volume volume isis thethe productproduct ofof thethe firstfirst 6 6 eigenvaueseigenvaues-- KK33 andand KK44 are are computedcomputed afterafter thethe dimensionsdimensions are are
renormalizedrenormalized to to havehave thethe samesame volumevolume
( ) ( ){ }∑∑= =
− −−=n
i
n
jji XXSXX
nK
1 1
31'
231
( ) ( ){ }∑=
− −−=n
iii XXSXXn
K1
21'
41
Redes de MercadoMarket shape as a precursor of crises and indicator of return to normality
07/09/97 17/09/97 27/09/97 07/10/97 17/10/97 27/10/97 06/11/97
102
K4
w=8 2nd Black Monday: 27/10/97
07/09/97 17/09/97 27/09/97 07/10/97 17/10/97 27/10/97 06/11/97
10-3
V
w=8 2nd Black Monday: 27/10/97
07/09/97 17/09/97 27/09/97 07/10/97 17/10/97 27/10/97 06/11/97850
900
950
1000
PS&
P500
28/08/97 07/09/97 17/09/97 27/09/97 07/10/97 17/10/97 27/10/97 06/11/97 16/11/97100
101
102
K3
w=8 2nd Black Monday: 27/10/97
Redes de MercadoMarket shape as a precursor of crises and indicator of return to normality
30/09/87 10/10/87 20/10/87 30/10/87 09/11/87 19/11/87 29/11/87 09/12/87 19/12/8710
−6
10−5
10−4
10−3
10−2
V
w=8 Black Monday: 19/10/1987
30/09/87 10/10/87 20/10/87 30/10/87 09/11/87 19/11/87 29/11/87 09/12/87 19/12/87200
250
300
350
PS
&P
500
30/09/87 10/10/87 20/10/87 30/10/87 09/11/87 19/11/87 29/11/87 09/12/87 19/12/8710
0
101
102
K3
w=8 Black Monday: 19/10/1987
30/09/87 10/10/87 20/10/87 30/10/87 09/11/87 19/11/87 29/11/87 09/12/87 19/12/8710
1
102
103
K4
w=8 Black Monday: 19/10/1987
- From some of the cases studied so far it looks as if the shape of the market might provide some precursors of impending crises and would also be an indicator of when normality has returned.
- However this is just work in progress. More to come.
Redes de MercadoMarket shape as a precursor of crises and indicator of return to normality
- RVM., T. Araújo and F. Louçã; Reconstructing an Economic Space from a Market Metric, Physica A 323 (2003) 625-648
- T. Araújo and F. Louçã; The Geometry of Crashes: A Measure of the Dynamics of Stock Market Crises, Quantitative Finance 7 (2007) 63-74
- T. Araújo and F. Louçã; The Seismography of Crashes in Financial Markets, Physics Letters A 372 (2008) 429-434
- T. Araújo and F. Louçã; Tribes under Threat - The Collective Behavior of Firms During Stock Market Crises, Working paper ISEG 2008/28, to appear in Int. Journ. of Industrial and Corporate Change
- T. Araújo and F. Louçã; Trouble Ahead - The Subprime Crisis as Evidence of a New Regime in the Stock Market, Working paper ISEG 2008/26, Economics Letters
Redes de MercadoReferences