DCC-GARCH for Volatility and Correlation Forecasting with Exogenous Market Signals
(2026) In Master's Theses in Mathematical Sciences FMSM01 20261Mathematical Statistics
- Abstract
- Financial markets exhibit time-varying volatility and cross-asset correlation. To construct
and optimize a risk-adjusted portfolio and account for underlying collinearity between se-
curities, a good understanding of these two dynamics is important. In this study global
equity indices are modeled with the purpose of improving the forecasting accuracy of
time-varying correlations, as well as distinguishing the difference between global multi-
variate and pairwise settings. A core part of this is the difference between a DCC-GARCH baseline model and its
numerous exogenous market signal customizations. Examples of these are the volatility
index, dark-pool activity index and credit spreads. Smaller models are compared with
the full... (More) - Financial markets exhibit time-varying volatility and cross-asset correlation. To construct
and optimize a risk-adjusted portfolio and account for underlying collinearity between se-
curities, a good understanding of these two dynamics is important. In this study global
equity indices are modeled with the purpose of improving the forecasting accuracy of
time-varying correlations, as well as distinguishing the difference between global multi-
variate and pairwise settings. A core part of this is the difference between a DCC-GARCH baseline model and its
numerous exogenous market signal customizations. Examples of these are the volatility
index, dark-pool activity index and credit spreads. Smaller models are compared with
the full model to question the efficacy of the multivariate approach.
The results show that the inclusion of some exogenous variables provide marginal im-
provement in predictive accuracy if added right, whilst some worsen it, either numeri-
cally or through added complexity. Credit spreads show modest but mostly beneficial
improvements, both for in sample fit and out-of-sample forecast errors for both the full
multivariate model and for the pairwise models. The volatility index showed nuanced
results, improving correlation forecasts for markets pairs such as US-Europe, while wors-
ening predictability for US-Asia pairs. DIX shows the weakest and least consistent effects,
suggesting dark pool activity carries limited information for global correlation dynamics
in our model. A recurring finding is that the DCC-GARCH baseline already captures
much of the dynamics that the exogenous signals might otherwise explain. Furthermore,
the model dimensionality affects the magnitude of market signal changes. A recurring
theme across all signals is that the extent of improvement is small. (Less) - Popular Abstract (Swedish)
- Under perioder av ökad marknadsoro tenderar världens börser att röra sig ännu mer
sammankopplat. I detta examensarbete undersöks om yttre marknadssignaler kan ge en
snabbare uppfattning om dessa korrelationer och huruvida de kan hjälpa till att förutse dessa
förändringar bättre och därmed ge upphov till bättre riskhantering.
Många investerare sprider sin risk genom att placera diversifierat på flera olika marknader. Tan-
ken är att om en marknad går dåligt så dämpas effekten i portföljen av att en annan går bra.
Men under kriser som finanskrisen 2008 och covidkraschen så tappar denna strategin sin effekt.
Marknader rörde sig väldigt samstämmigt, diversifiering skyddade inte lika bra och risken steg.
För investerare som... (More) - Under perioder av ökad marknadsoro tenderar världens börser att röra sig ännu mer
sammankopplat. I detta examensarbete undersöks om yttre marknadssignaler kan ge en
snabbare uppfattning om dessa korrelationer och huruvida de kan hjälpa till att förutse dessa
förändringar bättre och därmed ge upphov till bättre riskhantering.
Många investerare sprider sin risk genom att placera diversifierat på flera olika marknader. Tan-
ken är att om en marknad går dåligt så dämpas effekten i portföljen av att en annan går bra.
Men under kriser som finanskrisen 2008 och covidkraschen så tappar denna strategin sin effekt.
Marknader rörde sig väldigt samstämmigt, diversifiering skyddade inte lika bra och risken steg.
För investerare som förvaltar stora summor pensionskapital eller liknande blir dessa föränd-
ringar viktiga att förstå. Att kunna förutse samrörelser blir en viktig del av att förstå sig på sin
faktiska portföljrisk, där till synes okorrelerade placeringar kan följa varandra om man tittar ett
steg till. Detta examensarbete undersöker om yttre marknadssignaler som volatilitetsindex, kreditsprea-
dar eller dark-pool flöden kan ge bättre förmåga att förutse dessa förändringar. Modellen DCC-
GARCH ligger till grund för jämförelser mellan globala aktieindex där volatilitet och korrelation
fångas. Prognoser skapas och jämförs med en baslinje utan marknadsignaler. Resultatet visar
att det finns signal att hämta från dessa, men att förbättringar i prognoser oftast är mycket
modesta. Den mest konsekventa marknadssignalen var kreditspreaden, både sett till magnitud
på förbättring samt statistiska signifikansen.
En intressant diskussionspunkt är huruvida basmodellen fångar såpass mycket av volatilitets-
och korrelationsdynamiken att det finns ytterst lite utrymme för de yttre signalerna att påverka.
Resultaten tyder ofta på att externa signaler kan ge viss extra information, men att de sällan
räcker för att markant påverka prognoserna. För investerare innebär det att jakten på perfekta
riskprognoser fortsätter, där mer specifika och nischade modeller hade kunnat dra mer nytta av
signaler än vad globala aktieindex kan. (Less)
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/student-papers/record/9242629
- author
- Rosengren, Gustav LU and Torbiörnsson, Hugo
- supervisor
-
- Ted Kronvall LU
- organization
- course
- FMSM01 20261
- year
- 2026
- type
- H2 - Master's Degree (Two Years)
- subject
- publication/series
- Master's Theses in Mathematical Sciences
- report number
- LUTFMS-3567-2026
- ISSN
- 1404-6342
- other publication id
- 2026:E89
- language
- English
- id
- 9242629
- date added to LUP
- 2026-06-22 16:51:45
- date last changed
- 2026-07-13 15:50:42
@misc{9242629,
abstract = {{Financial markets exhibit time-varying volatility and cross-asset correlation. To construct
and optimize a risk-adjusted portfolio and account for underlying collinearity between se-
curities, a good understanding of these two dynamics is important. In this study global
equity indices are modeled with the purpose of improving the forecasting accuracy of
time-varying correlations, as well as distinguishing the difference between global multi-
variate and pairwise settings. A core part of this is the difference between a DCC-GARCH baseline model and its
numerous exogenous market signal customizations. Examples of these are the volatility
index, dark-pool activity index and credit spreads. Smaller models are compared with
the full model to question the efficacy of the multivariate approach.
The results show that the inclusion of some exogenous variables provide marginal im-
provement in predictive accuracy if added right, whilst some worsen it, either numeri-
cally or through added complexity. Credit spreads show modest but mostly beneficial
improvements, both for in sample fit and out-of-sample forecast errors for both the full
multivariate model and for the pairwise models. The volatility index showed nuanced
results, improving correlation forecasts for markets pairs such as US-Europe, while wors-
ening predictability for US-Asia pairs. DIX shows the weakest and least consistent effects,
suggesting dark pool activity carries limited information for global correlation dynamics
in our model. A recurring finding is that the DCC-GARCH baseline already captures
much of the dynamics that the exogenous signals might otherwise explain. Furthermore,
the model dimensionality affects the magnitude of market signal changes. A recurring
theme across all signals is that the extent of improvement is small.}},
author = {{Rosengren, Gustav and Torbiörnsson, Hugo}},
issn = {{1404-6342}},
language = {{eng}},
note = {{Student Paper}},
series = {{Master's Theses in Mathematical Sciences}},
title = {{DCC-GARCH for Volatility and Correlation Forecasting with Exogenous Market Signals}},
year = {{2026}},
}