dirk eddelbuettel, ph.d. debian andrprojects chicago, il...

Background About R and CRAN Finance Task View Selected Finance Packages Summary and Outlook

Using R in Finance

Dirk Eddelbuettel, Ph.D.Debian and R Projects

Invited Panel Presentation at the58th Midwest Finance Association Meetings

Chicago, IL, March 5, 2009

Dirk Eddelbuettel Using R in Finance

http://www.r-project.org




Outline

Background

About R and CRAN

Finance Task View

Selected Finance Packages

Summary and Outlook




Personal connections

I Financial Econometrician by training, with twelve+ years asa Quant in (Inv-)Banking, Hedge Funds, Prop Trading

I Debian developer/contributor since 1995I Debian R co-maintainer since 1999, maintainer since 2001I R package author or co-author:

I RQuantLib: R interface to the QuantLib librariesI digest: hash function ’digests’ of serialized R objectsI random: R interface to true RNG via random.orgI RDieHarder: R interface to DieHarder RNG testersI littler: R scripting front-endI RPostgreSQL: R interface to PostgreSQL RDBMSI Rcpp: C++ classes for extending R with C/C++ functionsI RInside: C++ classes for embedding R in C++ programs







random.org








Personal connections

I Other R Open Source activities:I R-SIG-Finance, R-SIG-Debian, R-SIG-HPC list ’owner’I Editor of CRAN Task Views Empirical Finance and High

Performance ComputingI Mentor for two R-related projects (cran2deb; RPostgreSQL)

at Google Summer of CodeI Co-organizer of the first R in Finance conference in April

2009, Chicago (http://www.RinFinance.com)I useR! Tutorial lecturer on High Performance Computing

with R in 2008 and 2009, also at R / FinanceI Other work-related R projects (spawning the CRAN

packages RLim, RBloomberg; others unreleased)I Quantian (live cdrom/dvd) author / developerI Associate Editor at Journal of Statistical Software





http://www.RinFinance.com





Outline

Background

About R and CRAN

Finance Task View


Summary and Outlook




Where are we right now with R ?

I R has grown tremendously in recent years, both in terms ofcapabilities and users.

I Widespread and increasing use in Finance.I S+ has been almost entirely eclipsed by R, much to the

chagrin of Insightful.I We now also have three companies offering commercial

support and extensions.I CRAN, the R package archive network, has grown

tremendously too: now north of 1600 packages.I There is more and more Finance content as shown in the

task view.








Illustration: Growth of r-help and r-sig-finance

Year

Mea

n N

umbe

r of

Mes

sage

s / M

onth

1997 1999 2001 2003 2005 2007

2050

100

200

500

1000

2000

●

●

●

●

●

●

●

●●

●●

●● R−HelpR−SIG−Finance

Source: Fox (2008, 2009), our calculations.

I Total R usage is difficultto measure.

I Mailing list activity issometimes used as aproxy.

I While r-help growth isslowing, several ’specialinterest group’ lists suchas r-sig-financeexperience stronggrowth.





Illustration: Growth of CRAN packagesN

umbe

r of

CR

AN

Pac

kage

s

2001

−06

−21

2001

−12

−17

2002

−06

−12

2003

−05

−27

2003

−11

−16

2004

−06

−05

2004

−10

−12

2005

−06

−18

2005

−12

−16

2006

−05

−31

2006

−12

−12

2007

−04

−12

2007

−11

−16

2008

−03

−18

2008

−10

−20

100

200

300

400

500

600

800

1000

1200

1400

1700

1.3

1.4

1.5

1.7

1.8

1.9

2.0

2.1

2.2

2.3

2.4

2.5

2.6

2.7

2.8

110

129

162

219

273

357406

548

647739

9111000

13001427

1679

●

●

●

●

●

●

●

●

●

●

●●

●●

●

Source: Fox (2008, 2009), our calculations

I John Fox provided thischart in an invited lectureat the last useR!meetings.

I Details, and moremetrics on R and thedynamics of the R Coregroup, are also in aforthcoming R News(soon: R Journal) article.








Aside: CRANberries

Source:

http://dirk.eddelbuettel.com/cranberries/

I The CRANberries feedsummarizes bothchanges to existingpackages, as well asnew packages.

I Implemented in 200 linesof R and using the tinyblosxom blog engine, itis available as a blog andvia an RSS feed.


http://dirk.eddelbuettel.com/cranberries/




Outline

Background

About R and CRAN

Finance Task View


Summary and Outlook




CRAN and CRAN Task View Finance

I Given 1600+ CRAN packages, navigation is difficult.I Idea suggested a few years ago to have topical views.I These Task Views are not perfect, but the best currently

available approach at navigating CRAN packages.I We created the Empirical Finance view around 2004 which

contains several sections onI standard regression modelsI time seriesI financeI risk managementI books / data setsI date and data management

I Rather than repeating the task view, let us illustrate severaldifferent packages.




Finance Task View




Outline

Background

About R and CRAN

Finance Task View


Summary and Outlook




RQuantLib (QuantLib Group; Eddelbuettel)

50 100 150

020

4060

80

option value

50 100 150

0.0

0.2

0.4

0.6

0.8

1.0

option delta

50 100 150

0.00

0.01

0.02

0.03

0.04

option gamma

50 100 150

010

2030

40

option vega

Strike is 100, maturity 1 year, riskless rate 0.03 Underlying price from 10 to 180

Volatility from 0.1 to 0.9

> example(EuropeanOptionArrays)

I QuantLib is a verycomplete and very wellwritten C++ library forquantitative finance.

I RQuantLib, firstreleased in 2002,provides access to asubset of QuantLib’sfunctionality directly fromR, in particular for(equity) option pricingand some yield curveanalysis.





Rmetrics (Wuertz et al)

● ● ●●●●●●●●●●● ●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●

●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●

●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●

●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●

●●●●●●●●●●●

1e−03 1e−02 1e−01 1e+00 1e+01

0.0

0.2

0.4

0.6

0.8

1.0

Excess Distribution

Fu(x−u)

x [lo

g S

cale

]

u =

0.0

0059

9

● ● ●●●●●●●●●●● ●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●

●

●

●

1e−03 1e−02 1e−01 1e+00 1e+01

5e−

045e

−03

5e−

025e

−01

Tail of Underlying Distribution

x [log scale]

1−F

(x)

[log

scal

e]

●

●

●

●

●

●●

●

●●●

●

●

●●●

●

●●

●●

●

●

●

●

●

●

●

●

●●

●

●●●

●

●

●

●

●

●

●

●

●

●●

●●

●●●●●

●

●●

●

●

●

●

●

●

●●

●

●

●

●

●

●

●

●

●

●

●

●

●

●

●

●●

●

●

●

●

●

●●●

●

●

●

●●

●

●

●

●

●●●

●

●

●●●

●

●

●

●

●

●●●

●

●●●●

●

●●●●

●●

●

●●

●

●

●

●

●

●

●

●

●●●

●

●

●●

●

●●

●

●

●

●

●

●

●

●●

●

●

●●

●

●

●

●

●

●

●●

●

●

●

●

●

●

●●

●●

●

●

●

●

●

●

●●

●

●

●

●

●●

●●

●

●

●

●

●●●

●

●

●

●

●

●

●

●

●

●

●

●

●

●

●

●

●

●

●●

●

●●

●●

●

●

●

●

●

●

●

●

●

●

●●●●

●

●

●

●

●

●

●

●

●

●●

●

●

●

●

●

●

●

●●

●

●

●●●

●

●

●

●

●

●

●

●

●●●

●

●

●●

●

●

●

●

●

●

●

●

●

●

●

●

●

●

●

●

●●

●

●

●

●

●

●●

●

●●

●

●

●

●

●

●●

●●

●

●

●

●

●●

●

●

●

●

●

●●●

●●

●

●

●

●

●

●

●

●●

●

●

●

●

●

●

●

●

●

●

●

●●

●

●●

●●●

●

●

●●

●

●

●

●●

●

●

●

●

●

●

●

●

●

●

●●

●

●

●

●●●●

●

●

●●●

●●

●

●

●

●

●

●●

●

●●

●●

●

●

●●

●

●

●●

●

●

●

●

●●

●

●

●

●

●

●

●

●

●●

●

●

●

●●

●

●●

●

●

●

●

●

●●

●

●

●

●

●

●

●

●

●

●

●

●

●

●●

●●●

●

●●

●

●

●

●

●

●●

●●●

●

●

●

●

●

●

●

●

●

●●●●

●

●

●

●

●

●

●

●

●

●●

●

●

●

●●

●

●

●

●

●

●

●

●

●

●

●

●

●●

●

●

●

●

●

●

●●

●

●

●

●

●

●

●

●

●

●

●●●●

●

●

●

●

●●

●

●

●

●●

●

●

●

●●

●

●

●

●

●

●●

●

●

●●●

●

●

●

●

●

●

●

●

●

●

●●

●●

●●

●

●

●

●

●●

●

●

●

●

●●

●

●

●

●

●

●●

●●

●

●

●

●

●

●

●

●●●

●

●

●

●

●

●

●

●

●

●

●

●

●

●

●●●

●

●

●

●●

●

●

●●

●

●

●●

●

●●

●

●

●

●

●

●

●●

●

●●

●

●

●●●

●●

●

●

●●

●

●

●

●●●●

●

●

●

●

●

●

●

●

●

●●

●●

●

●

●

●

●

●●

●

●

●

●

●●●●

●●

●

●●

●

●●●

●

●

●●

●●

●

●

●

●

●●

●

●

●

●●

●

●●●●

●

●

●●

●

●●●

●●●

●

●

●

●●

●

●

●

●

●

●

●

●

●

●

●

●

●

●

●

●

●●

●●

●●

●●

●

●●

●

●

●

●●●

●

●●

●

●

●

●

●

●●●

●

●●

●●

●

●●●●

●

●

●

●

●

●●

●●

●

●●

●

●

●

●

●

●

●●●

●

●

●●●

●

●●

●

●

●

●

●

●

●●

●

●

●

●

●●

●●

●

●

●●●

●

●

●

●

●

●●●

●

●

●

●●●

●●●●

●

●

●

●

●●●

●

●

●

●

●

●

●

●

●

●

●

●

●●

●

●●

●

●

●

●●

●

●●●

●

●

●

●

●

●

●

●

●

●●

●

●

●●

●

●

●

●

●

●

●

●

●

●

●

●

●

●

●

●●

●

●●

●

●●

●

●

●

●

●●

●●

●

●

●

●●●

●

●●

●

●

●

●

●

●

●

●

●●

●

●

●

●

●

●●

●●●

●

●●

●

●

●●●●

●

●

●●

●

0 200 400 600 800 1000

01

23

45

6

Scatterplot of Residuals

Ordering

Res

idua

ls

●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●

●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●

●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●

●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●

●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●

●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●

●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●

●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●●

●●●●●●●●●●●●●●●●●●●●●●●●●

●●●●●●●●●●●●●●●●●●●●●●●●●●●

●●●●●●●●●●●●●●●●●●

●●●●●●●●●●●●●●

● ●●●●●●

●●●●●

●●●●●

●●

●

●

●

0 1 2 3 4 5 6

02

46

QQ−Plot of Residuals

Ordered Data

Exp

onen

tial Q

uant

iles

> example(GpdModelling)

I Rmetrics, first releasedin 2004 is acomprehensive set of Rpackages.

I It covers time series,GARCH and volatilitymodeling, Extreme ValueTheory and Copulae,derivative pricing,portfolio analysis,optimization and more.






portfolio (Enos, Kane et al)

Cumulative Spread Return

Ret

urn

(%)

−20−10

01020

Mar May Jul Sep Nov

Total return: −2.7

Worst drawdown: −9

cap.usd

Mar May Jul Sep Nov

Total return: 28

Worst drawdown: −−

smi

Cumulative Quantile Return

Date

Ret

urn

(%)

0

10

20

30

Mar May Jul Sep Nov

cap.usd

Mar May Jul Sep Nov

smi

quantilehighQ9Q8Q7Q6Q5Q4Q3Q2low

> example(backtest)

I The portfoliopackage provides codeand data for real-lifeequity long/short portfolioanalysis.

I The portfolioSimpackage adds simulationsupport; the tradeCostpackage analysesex-post trade impact, andthe backtest packagepermits to test portfolios.




PerformanceAnalytics (Carl and Peterson)

Equity.Market.Neutral

Returns

Den

sity

−0.010 −0.005 0.000 0.005 0.010 0.015 0.020 0.025

020

4060

8010

0

99 %

Mod

VaR

99%

VaR

> example(chart.Histogram)

I This package provides alibrary of econometricfunctions forperformance and riskanalysis of financialportfolios.

I It offers practioners andresearcher some of thelatest research inanalysis of both normaland non-normal returnstreams.




Outline

Background

About R and CRAN

Finance Task View


Summary and Outlook




Summary

I R is a very vibrant platform for data analysis, visualizationand programming with data.

I Hence, R provides an excellent platform for academicresearch and teaching — as well as investment researchand trading.

I Finance has traditionally been one of the two key users ofthe S language, and this constiuency has moved from S+to R.

I The number of dedicated Finance packages for R isincreasing as well, the R-Forge site is a good place towatch (http://R-Forge.R-Project.org).






http://R-Forge.R-Project.org



Outlook

If you don’t go with R now, you will someday.– David Kane on r-sig-finance, 30 Nov 2004





R / Finance in April 2009




Contact

http://dirk.eddelbuettel.com

[email protected]


http://dirk.eddelbuettel.com

[email protected]


dirk eddelbuettel, ph.d. debian andrprojects chicago, il...

Documents