SlideShare a Scribd company logo
1 of 47
Download to read offline
Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018
Delta Hedging via Machine Learning
(w/o parametric models).*
Thomas F. Coleman
Director, WatRISQ
University of Waterloo
* Learning Minimum Variance Discrete Hedging Directly from the Market
Journal of Quantitative Finance, 2017. Ke Nian, Yuying Li, Thomas F. Coleman
Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018
Seminar last week on Wall St : machine learning, text, arbitrage…
Speaker: Arun Verma, Bloomberg
“Machine Learning & Sentiment Analysis in Finance for Statistical
Arbitrage”
Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018
Seminar last week on Wall St : machine learning, text, arbitrage…
Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018
Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018
Delta Hedging via Machine Learning
(w/o parametric models).*
Thomas F. Coleman
Director, WatRISQ
University of Waterloo
* Learning Minimum Variance Discrete Hedging Directly from the Market
Journal of Quantitative Finance, 2017. Ke Nian, Yuying Li, Thomas F. Coleman
Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018
The Big Picture Message
Machine learning technology, w/o any finance knowledge or built-in
finance models, can (sometimes) outperform highly developed
specialized finance models in important (predictive) finance tasks.
Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018
The Big Picture Message
Machine learning technology, w/o any finance knowledge or built-in
finance models, can (sometimes) outperform highly developed
specialized finance models in important (predictive) finance tasks.
We illustrate this on one of the most important and well-studied problems
in finance : option hedging.
Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018
The Big Picture Message
Machine learning technology, w/o any finance knowledge or built-in
finance models, can (sometimes) outperform highly developed
specialized finance models in important (predictive) finance tasks.
We illustrate this on one of the most important and well-studied problems
in finance : option hedging.
The success we report is definitive.
Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018
Hedging options is a major task in computational finance to remove
market risk .
Typical process (delta hedge):
1. Choose an option model
2. Calibrate the model (using real price(s)) to estimate model
parameters
3. Differentiate the model (with parameters now determined) at
current point to determine delta hedge
Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018
Hedging options is a major task in computational finance to remove
market risk .
Typical process (delta hedge):
1. Choose an option model
2. Calibrate the model (using real price(s)) to estimate model
parameters
3. Differentiate the model (with parameters now determined) at
current point to determine delta hedge
BUT: - fails to capture parameter dependence on underlying
- does not minimize variance of hedge risk
Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018
Practitioner's BS delta hedging for an option:
1. Assume that the underlying follows a BS underlying price model:
( )t t t tdS r q S dt S dW  
Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018
Practitioner's BS delta hedging for an option:
1. Assume that the underlying follows a BS underlying price model:
2. Calibrate BS implied volatility
from the market option price
( )t t t tdS r q S dt S dW  
MKTV
( ; )BS MKTV S V 
Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018
Practitioner's BS delta hedging for an option:
1. Assume that the underlying follows a BS underlying model:
2. Calibrate BS implied volatility
from the market option price
3. Compute the BS delta using implied vol
( )t t t tdS r q S dt S dW  

MKTV
( ; )BS MKTV S V 
BSV
S


Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018
0In Coleman et al (2001) we illustrated the dependence of on S
Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018
Minimum Variance Hedging
Goal: minimize option risk minimize variance (MV) in hedging error.
Let
: instantaneous change in underlying
: instantaneous change in option value
: position in underlying for a MV strategy
Hedging error:
MV delta hedging:
dS
dV
MV
MVdV dS
min variance ( ) (1)MV MVdV dS 
Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018
For example, Hull and White [2017] directly attack (1) by assuming
Using market data to determine parameters a,b,c
Hull and White approximate
E( )BS BS
MV
V V
S S



  
  
  
2
E( ) ( )BS BS
a b c
S S T
    


Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018
For example, Hull and White [] directly attack (1) by assuming
Using market data to determine parameters a,b,c
Hull and White approximate
Improved results are obtained using this correction to BS-delta:
E( )BS BS
MV
V V
S S



  
  
  
2
E( ) ( )BS BS
a b c
S S T
    


2
( )
( )
BS BS
BS BS
MV
a b c
vega
S T
 
 
 
 
Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018
Our new data-driven approach:
Solve
directly from the market data : no option models: use (standard) ML
techniques directly
min variance ( ) (1)MV MVdV dS 
Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018
Our new approach:
solve
directly from the market data : no option models: use (standard) ML
techniques directly
min variance ( ) (1)MV MVdV dS 
learn
Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018
A Machine Learning Primer
Given m training points:
Where
x: feature vector
y: target (or outcome)
A regularized kernel method learns a nonlinear function
to capture the dependence between target y and feature vector x.
is then used to ‘predict’ y for feature selection x
1 1{( , ),...,( , )}m mx y x y
( )f x
( )f x
Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018
A Machine Learning Primer
Given m training points:
Where
x: feature vector
y: target (or outcome)
A regularized kernel method learns a nonlinear function
to capture the dependence between target y and feature vector x.
is then used to ‘predict’ y for feature selection x
Choose a positive definite kernel: e.g.,
1 1{( , ),...,( , )}m mx y x y
( )f x
( )f x
2
2
2
'
2
( , ')
x x
k x x e 



Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018
A Machine Learning Primer
Given m training points:
Where
x: feature vector
y: target (or outcome)
A regularized kernel method learns a nonlinear function
to capture the dependence between target y and feature vector x.
is then used to ‘predict’ y for feature selection x
Choose a positive definite kernel: e.g.,
A regularized regression problem:
1 1{( , ),...,( , )}m mx y x y
( )f x
( )f x
2
2
2
'
2
( , ')
x x
k x x e 



Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018
A regularized (nonlinear) regression problem (to determine (learn)
parameters that define ) :
2
1
1
min ( , ( )) ,
e.g., ( , ( )) ( )
m
f i i
i
p
i i i i
L y f x f
m
L y f x y f x
 

 
 
 
 

Defined by choice of K
f
Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018
A regularized (nonlinear) regression problem:
2
1
1
min ( , ( )) ,
e.g., ( , ( )) ( )
m
f i i
i
p
i i i i
L y f x f
m
L y f x y f x
 

 
 
 
 

Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018
A regularized (nonlinear) regression problem:
where m-vector minimizes the pos def quadratic:
2
1
1
min ( , ( )) ,
e.g., ( , ( )) ( )
m
f i i
i
p
i i i i
L y f x f
m
L y f x y f x
 

 
 
 
 

1
( ) ( , )
m
i i
i
f x k x x

 

2
1 1 1 1
min { ( ( , )) ( , )}m
m m m m
i j i j i j i j
i j i j
y k x x k x x
   
   
   
Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018
A regularized (nonlinear) regression problem:
where m-vector minimizes the pos def quadratic:
or
2
1
1
min ( , ( )) ,
e.g., ( , ( )) ( )
m
f i i
i
p
i i i i
L y f x f
m
L y f x y f x
 

 
 
 
 

1
( ) ( , )
m
i i
i
f x k x x

 

2
1 1 1 1
min { ( ( , )) ( , )}m
m m m m
i j i j i j i j
i j i j
y k x x k x x
   
   
   
2
2
min { }, where ( , )T
ij i jy K K K k x x     
Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018
A regularized (nonlinear) regression problem:
where m-vector minimizes the pos def quadratic:
or
or
2
1
1
min ( , ( )) ,
e.g., ( , ( )) ( )
m
f i i
i
p
i i i i
L y f x f
m
L y f x y f x
 

 
 
 
 

1
( ) ( , )
m
i i
i
f x k x x

 

2
1 1 1 1
min { ( ( , )) ( , )}m
m m m m
i j i j i j i j
i j i j
y k x x k x x
   
   
   
2
2
min { }, where ( , )T
ij i jy K K K k x x     
1
( )K I y  
 
Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018
Recipe for determining ML model
1. Choose feature vector x , kernel k
2. Get data
3. Form m-by-m matrix
4. Determine (cross validation)
5. Solve
( , ), 1:i ix y i m
( ( , ))i jK k x x
( )K I y  

Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018
Recipe for determining ML model
1. Choose feature vector x , kernel k
2. Get data
3. Form m-by-m matrix
4. Determine (cross validation)
5. Solve
Prediction:
( , ), 1:i ix y i m
( ( , ))i jK k x x
( )K I y  

1
( ) ( , )
m
pred i i
i
y x k x x

 
Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018
To apply to our problem:
1. What is feature vector x?
2. Kernel function k?
3. Data?
4. Choose
And most importantly

Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018
To apply to our problem:
1. What is feature vector x?
2. Kernel function k?
3. Data?
4. Choose
And most importantly, what is objective function:

2
1
1
min ( , ( ))
m
f i i
i
L y f x f
m
 

 
 
 

min variance ( )MV MVdV dS 
Key!
Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018
Learn hedging function directly from the market using ML
approach: let be a positive definite kernel
where denotes change in (observed) market price
Solution is
( )f x
22
1
1
min ( ( ))
m
f i i i
i
V S f x f
m
 

 
    
 

t
i i iV V V
  
1
( ) ( , )
m
i i
i
f x k x x

 
( , ')k x x
Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018
Learn hedging function directly from the market using ML
approach: let be a positive definite kernel.
where denotes change in (observed) market price
Solution is
Where solves the pos def. quadratic minimization:
Features x = moneyness , time-to-expiry;
( )f x
22
1
1
min ( ( ))
m
f i i i
i
V S f x f
m
 

 
    
 

t
i i iV V V
  
1
( ) ( , )
m
i i
i
f x k x x

 
( , ')k x x

2
1 1 1 1
min { ( ( ( , )) ( , )}m
m m m m
i i i i j i j i j
i i i j
V S k x x k x x
   
   
     
BS
( )
S
strike
Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018
Empirical Results
Data: S&P 500 index option data from the OptionMetric Database
data: January 2, 2004 to August 31, 2015
Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018
Empirical Results
Data: S&P 500 index option data from the OptionMetric Database
data: January 2, 2004 to August 31, 2015
Methods compared:
MV: Hull-White's minimum variance hedging based on formulation
LVF: MV hedging using correction based on LVF analysis
BS: implied volatility BS delta hedging
SABR : MV hedging from SABR stochastic volatility.
DKLSPL : direct learning a spline kernel hedging function
Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018
Empirical Results
Data: S&P 500 index option data from the OptionMetric Database
data: January 2, 2004 to August 31, 2015
Methods compared:
MV: Hull-White's minimum variance hedging based on formulation
LVF: MV hedging using correction based on LVF analysis
BS: implied volatility BS delta hedging
SABR : MV hedging from SABR stochastic volatility.
DKLSPL : direct learning a spline kernel hedging function
Performance Measure:
2
1
2
1
( )
( )
m
M
i i
i
m
BS
i i
i
V S
GAIN
V S




  

  


Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018
Empirical Testing
Data: S&P 500 index option data from the OptionMetric Database
data: January 2, 2004 to August 31, 2015
Sliding window:
3 years data 1 mth-out-of sample
learning model testing
9 buckets, 9 models
Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018
9 buckets, 9 models
Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018
Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018
Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018
Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018
Concluding remarks
We have proposed to learn the hedge function directly from market data
(using ML techniques).
Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018
Concluding remarks
We have proposed to learn the hedge function directly from market
data (using ML techniques).
Empirical results show
- proposed approach definitively outperforms existing MV hedge
methods in daily hedging
Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018
Concluding remarks
We have proposed to learn the hedge function directly from market data
(using ML techniques).
Empirical results show
- proposed approach definitively outperforms existing MV hedge
methods in daily hedging
- proposed approach definitively outperforms implied vol BS hedge
in daily, weekly and monthly hedging
Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018
Concluding remarks
We have proposed to learn the hedge function directly from market data
(using ML techniques).
Empirical results show
- proposed approach definitively outperforms existing MV hedge
methods in daily hedging
- proposed approach definitively outperforms implied vol BS hedge
in daily, weekly and monthly hedging
Question: What other important (predictive) problems in finance,
traditionally solved with highly developed specialized finance models,
are amenable to general data driven machine learning techniques?
Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018
REFERENCES
T. F. Coleman, Y. Kim, Y. Li, A. Verma, Dynamic hedging with a deterministic
local volatility function model, The Journal of Risk 5 (2001) 63:89.
J. Hull, A. White, Optimal delta hedging for options Journal of Banking &
Finance, 82:180-190, 2017
G. Bakshi, C. Cao, Z. Chen, Empirical performance of alternative option pricing
models, The Journal of Finance 52 (1997) 2003.
S. Crepey, Delta-hedging vega risk, Quantitative Finance 4 (2004) 559{579.
G. Bakshi, C. Cao, Z. Chen, The Journal of Finance 52 (1997) 2003{2049.
K. P. R., R. Schenk-Hoppe, C.-O. Ewald, Risk minimization in stochastic
volatility models: model risk and empirical performance, Quantitative Finance 9
(2009) 693{704.
G. Bakshi, C. Cao, Z. Chen, The Journal of Finance 52 (1997) 2003.
J. Hutchinson, A. Lo, T. Poggio. A nonparametric approach to pricing
and hedging derivative securities via learning networks. The Journal
of Finance. 49(3):851-889, 1994
Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018

More Related Content

Similar to MLX 2018 - Thomas F. Coleman, University of Waterloo

Andrew_Hair_Assignment_3
Andrew_Hair_Assignment_3Andrew_Hair_Assignment_3
Andrew_Hair_Assignment_3
Andrew Hair
 
Mb0048 operations research
Mb0048   operations researchMb0048   operations research
Mb0048 operations research
smumbahelp
 
isabelle_webinar_jan..
isabelle_webinar_jan..isabelle_webinar_jan..
isabelle_webinar_jan..
butest
 
Data mining seminar report
Data mining seminar reportData mining seminar report
Data mining seminar report
mayurik19
 

Similar to MLX 2018 - Thomas F. Coleman, University of Waterloo (20)

A FRIENDLY APPROACH TO PARTICLE FILTERS IN COMPUTER VISION
A FRIENDLY APPROACH TO PARTICLE FILTERS IN COMPUTER VISIONA FRIENDLY APPROACH TO PARTICLE FILTERS IN COMPUTER VISION
A FRIENDLY APPROACH TO PARTICLE FILTERS IN COMPUTER VISION
 
Mobile data offloading
Mobile data offloadingMobile data offloading
Mobile data offloading
 
MAB-ppt.pdf
MAB-ppt.pdfMAB-ppt.pdf
MAB-ppt.pdf
 
Decision Making Process
Decision Making ProcessDecision Making Process
Decision Making Process
 
Andrew_Hair_Assignment_3
Andrew_Hair_Assignment_3Andrew_Hair_Assignment_3
Andrew_Hair_Assignment_3
 
Application Of Local Search Methods For Solving A Quadratic Assignment Probl...
Application Of Local Search Methods For Solving  A Quadratic Assignment Probl...Application Of Local Search Methods For Solving  A Quadratic Assignment Probl...
Application Of Local Search Methods For Solving A Quadratic Assignment Probl...
 
pam_1997
pam_1997pam_1997
pam_1997
 
AMAZON STOCK PRICE PREDICTION BY USING SMLT
AMAZON STOCK PRICE PREDICTION BY USING SMLTAMAZON STOCK PRICE PREDICTION BY USING SMLT
AMAZON STOCK PRICE PREDICTION BY USING SMLT
 
PREDICTIVE EVALUATION OF THE STOCK PORTFOLIO PERFORMANCE USING FUZZY CMEANS A...
PREDICTIVE EVALUATION OF THE STOCK PORTFOLIO PERFORMANCE USING FUZZY CMEANS A...PREDICTIVE EVALUATION OF THE STOCK PORTFOLIO PERFORMANCE USING FUZZY CMEANS A...
PREDICTIVE EVALUATION OF THE STOCK PORTFOLIO PERFORMANCE USING FUZZY CMEANS A...
 
CNSM 2022 - An Online Framework for Adapting Security Policies in Dynamic IT ...
CNSM 2022 - An Online Framework for Adapting Security Policies in Dynamic IT ...CNSM 2022 - An Online Framework for Adapting Security Policies in Dynamic IT ...
CNSM 2022 - An Online Framework for Adapting Security Policies in Dynamic IT ...
 
Mb0048 operations research
Mb0048   operations researchMb0048   operations research
Mb0048 operations research
 
isabelle_webinar_jan..
isabelle_webinar_jan..isabelle_webinar_jan..
isabelle_webinar_jan..
 
Data mining seminar report
Data mining seminar reportData mining seminar report
Data mining seminar report
 
Metric-learn, a Scikit-learn compatible package
Metric-learn, a Scikit-learn compatible packageMetric-learn, a Scikit-learn compatible package
Metric-learn, a Scikit-learn compatible package
 
Statistical Modeling: The Two Cultures
Statistical Modeling: The Two CulturesStatistical Modeling: The Two Cultures
Statistical Modeling: The Two Cultures
 
Quantum Business in Japanese Market
Quantum Business in Japanese MarketQuantum Business in Japanese Market
Quantum Business in Japanese Market
 
AINL 2016: Strijov
AINL 2016: StrijovAINL 2016: Strijov
AINL 2016: Strijov
 
A computational scientist's wish list for tomorrow's computing systems
A computational scientist's wish list for tomorrow's computing systemsA computational scientist's wish list for tomorrow's computing systems
A computational scientist's wish list for tomorrow's computing systems
 
IRJET - Stock Market Prediction using Machine Learning Algorithm
IRJET - Stock Market Prediction using Machine Learning AlgorithmIRJET - Stock Market Prediction using Machine Learning Algorithm
IRJET - Stock Market Prediction using Machine Learning Algorithm
 
increasing the action gap - new operators for reinforcement learning
increasing the action gap - new operators for reinforcement learningincreasing the action gap - new operators for reinforcement learning
increasing the action gap - new operators for reinforcement learning
 

Recently uploaded

TriStar Gold- 05-13-2024 corporate presentation
TriStar Gold- 05-13-2024 corporate presentationTriStar Gold- 05-13-2024 corporate presentation
TriStar Gold- 05-13-2024 corporate presentation
Adnet Communications
 
一比一原版(UC Davis毕业证书)加州大学戴维斯分校毕业证成绩单学位证书
一比一原版(UC Davis毕业证书)加州大学戴维斯分校毕业证成绩单学位证书一比一原版(UC Davis毕业证书)加州大学戴维斯分校毕业证成绩单学位证书
一比一原版(UC Davis毕业证书)加州大学戴维斯分校毕业证成绩单学位证书
atedyxc
 
一比一原版(Cornell毕业证书)康奈尔大学毕业证成绩单学位证书
一比一原版(Cornell毕业证书)康奈尔大学毕业证成绩单学位证书一比一原版(Cornell毕业证书)康奈尔大学毕业证成绩单学位证书
一比一原版(Cornell毕业证书)康奈尔大学毕业证成绩单学位证书
atedyxc
 
DSP Gold ETF Fund of Fund PPT - April'2024
DSP Gold ETF Fund of Fund PPT - April'2024DSP Gold ETF Fund of Fund PPT - April'2024
DSP Gold ETF Fund of Fund PPT - April'2024
DSP Mutual Fund
 
SAUDI ARABIYA | +966572737505 |Jeddah Get Cytotec pills for Abortion pills
SAUDI ARABIYA | +966572737505 |Jeddah Get Cytotec pills for Abortion pillsSAUDI ARABIYA | +966572737505 |Jeddah Get Cytotec pills for Abortion pills
SAUDI ARABIYA | +966572737505 |Jeddah Get Cytotec pills for Abortion pills
Abortion pills in Riyadh +966572737505 get cytotec
 
一比一原版(WashU毕业证书)圣路易斯华盛顿大学毕业证成绩单学位证书
一比一原版(WashU毕业证书)圣路易斯华盛顿大学毕业证成绩单学位证书一比一原版(WashU毕业证书)圣路易斯华盛顿大学毕业证成绩单学位证书
一比一原版(WashU毕业证书)圣路易斯华盛顿大学毕业证成绩单学位证书
atedyxc
 
一比一原版(SFU毕业证书)西蒙菲莎大学毕业证成绩单学位证书
一比一原版(SFU毕业证书)西蒙菲莎大学毕业证成绩单学位证书一比一原版(SFU毕业证书)西蒙菲莎大学毕业证成绩单学位证书
一比一原版(SFU毕业证书)西蒙菲莎大学毕业证成绩单学位证书
atedyxc
 
State Space Tutorial.pptxjjjjjjjjjjjjjjj
State Space Tutorial.pptxjjjjjjjjjjjjjjjState Space Tutorial.pptxjjjjjjjjjjjjjjj
State Space Tutorial.pptxjjjjjjjjjjjjjjj
joshuaclack73
 

Recently uploaded (20)

TriStar Gold- 05-13-2024 corporate presentation
TriStar Gold- 05-13-2024 corporate presentationTriStar Gold- 05-13-2024 corporate presentation
TriStar Gold- 05-13-2024 corporate presentation
 
How to exchange my pi coins on HTX in 2024
How to exchange my pi coins on HTX in 2024How to exchange my pi coins on HTX in 2024
How to exchange my pi coins on HTX in 2024
 
一比一原版(UC Davis毕业证书)加州大学戴维斯分校毕业证成绩单学位证书
一比一原版(UC Davis毕业证书)加州大学戴维斯分校毕业证成绩单学位证书一比一原版(UC Davis毕业证书)加州大学戴维斯分校毕业证成绩单学位证书
一比一原版(UC Davis毕业证书)加州大学戴维斯分校毕业证成绩单学位证书
 
一比一原版(Cornell毕业证书)康奈尔大学毕业证成绩单学位证书
一比一原版(Cornell毕业证书)康奈尔大学毕业证成绩单学位证书一比一原版(Cornell毕业证书)康奈尔大学毕业证成绩单学位证书
一比一原版(Cornell毕业证书)康奈尔大学毕业证成绩单学位证书
 
Managing personal finances wisely for financial stability and
Managing personal finances wisely for financial stability  andManaging personal finances wisely for financial stability  and
Managing personal finances wisely for financial stability and
 
DIGITAL COMMERCE SHAPE VIETNAMESE SHOPPING HABIT IN 4.0 INDUSTRY
DIGITAL COMMERCE SHAPE VIETNAMESE SHOPPING HABIT IN 4.0 INDUSTRYDIGITAL COMMERCE SHAPE VIETNAMESE SHOPPING HABIT IN 4.0 INDUSTRY
DIGITAL COMMERCE SHAPE VIETNAMESE SHOPPING HABIT IN 4.0 INDUSTRY
 
DSP Gold ETF Fund of Fund PPT - April'2024
DSP Gold ETF Fund of Fund PPT - April'2024DSP Gold ETF Fund of Fund PPT - April'2024
DSP Gold ETF Fund of Fund PPT - April'2024
 
SAUDI ARABIYA | +966572737505 |Jeddah Get Cytotec pills for Abortion pills
SAUDI ARABIYA | +966572737505 |Jeddah Get Cytotec pills for Abortion pillsSAUDI ARABIYA | +966572737505 |Jeddah Get Cytotec pills for Abortion pills
SAUDI ARABIYA | +966572737505 |Jeddah Get Cytotec pills for Abortion pills
 
一比一原版(WashU毕业证书)圣路易斯华盛顿大学毕业证成绩单学位证书
一比一原版(WashU毕业证书)圣路易斯华盛顿大学毕业证成绩单学位证书一比一原版(WashU毕业证书)圣路易斯华盛顿大学毕业证成绩单学位证书
一比一原版(WashU毕业证书)圣路易斯华盛顿大学毕业证成绩单学位证书
 
Understanding China(International Trade-Chinese Model of development-Export l...
Understanding China(International Trade-Chinese Model of development-Export l...Understanding China(International Trade-Chinese Model of development-Export l...
Understanding China(International Trade-Chinese Model of development-Export l...
 
1. Elemental Economics - Introduction to mining
1. Elemental Economics - Introduction to mining1. Elemental Economics - Introduction to mining
1. Elemental Economics - Introduction to mining
 
How can I withdraw my pi coins to real money in India.
How can I withdraw my pi coins to real money in India.How can I withdraw my pi coins to real money in India.
How can I withdraw my pi coins to real money in India.
 
How do I sell my Pi Network currency in 2024?
How do I sell my Pi Network currency in 2024?How do I sell my Pi Network currency in 2024?
How do I sell my Pi Network currency in 2024?
 
project ratio analysis of bcom studies .
project ratio analysis of bcom studies .project ratio analysis of bcom studies .
project ratio analysis of bcom studies .
 
Diversification in Investment Portfolio.pdf
Diversification in Investment Portfolio.pdfDiversification in Investment Portfolio.pdf
Diversification in Investment Portfolio.pdf
 
Slideshare - ONS Economic Forum Slidepack - 13 May 2024.pptx
Slideshare - ONS Economic Forum Slidepack - 13 May 2024.pptxSlideshare - ONS Economic Forum Slidepack - 13 May 2024.pptx
Slideshare - ONS Economic Forum Slidepack - 13 May 2024.pptx
 
一比一原版(SFU毕业证书)西蒙菲莎大学毕业证成绩单学位证书
一比一原版(SFU毕业证书)西蒙菲莎大学毕业证成绩单学位证书一比一原版(SFU毕业证书)西蒙菲莎大学毕业证成绩单学位证书
一比一原版(SFU毕业证书)西蒙菲莎大学毕业证成绩单学位证书
 
State Space Tutorial.pptxjjjjjjjjjjjjjjj
State Space Tutorial.pptxjjjjjjjjjjjjjjjState Space Tutorial.pptxjjjjjjjjjjjjjjj
State Space Tutorial.pptxjjjjjjjjjjjjjjj
 
Pitch-deck CopyFinancial and MemberForex.ppsx
Pitch-deck CopyFinancial and MemberForex.ppsxPitch-deck CopyFinancial and MemberForex.ppsx
Pitch-deck CopyFinancial and MemberForex.ppsx
 
STRATEGIC MANAGEMENT VIETTEL TELECOM GROUP
STRATEGIC MANAGEMENT VIETTEL TELECOM GROUPSTRATEGIC MANAGEMENT VIETTEL TELECOM GROUP
STRATEGIC MANAGEMENT VIETTEL TELECOM GROUP
 

MLX 2018 - Thomas F. Coleman, University of Waterloo

  • 1. Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018 Delta Hedging via Machine Learning (w/o parametric models).* Thomas F. Coleman Director, WatRISQ University of Waterloo * Learning Minimum Variance Discrete Hedging Directly from the Market Journal of Quantitative Finance, 2017. Ke Nian, Yuying Li, Thomas F. Coleman
  • 2. Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018 Seminar last week on Wall St : machine learning, text, arbitrage… Speaker: Arun Verma, Bloomberg “Machine Learning & Sentiment Analysis in Finance for Statistical Arbitrage”
  • 3. Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018 Seminar last week on Wall St : machine learning, text, arbitrage…
  • 4. Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018
  • 5. Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018 Delta Hedging via Machine Learning (w/o parametric models).* Thomas F. Coleman Director, WatRISQ University of Waterloo * Learning Minimum Variance Discrete Hedging Directly from the Market Journal of Quantitative Finance, 2017. Ke Nian, Yuying Li, Thomas F. Coleman
  • 6. Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018 The Big Picture Message Machine learning technology, w/o any finance knowledge or built-in finance models, can (sometimes) outperform highly developed specialized finance models in important (predictive) finance tasks.
  • 7. Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018 The Big Picture Message Machine learning technology, w/o any finance knowledge or built-in finance models, can (sometimes) outperform highly developed specialized finance models in important (predictive) finance tasks. We illustrate this on one of the most important and well-studied problems in finance : option hedging.
  • 8. Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018 The Big Picture Message Machine learning technology, w/o any finance knowledge or built-in finance models, can (sometimes) outperform highly developed specialized finance models in important (predictive) finance tasks. We illustrate this on one of the most important and well-studied problems in finance : option hedging. The success we report is definitive.
  • 9. Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018 Hedging options is a major task in computational finance to remove market risk . Typical process (delta hedge): 1. Choose an option model 2. Calibrate the model (using real price(s)) to estimate model parameters 3. Differentiate the model (with parameters now determined) at current point to determine delta hedge
  • 10. Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018 Hedging options is a major task in computational finance to remove market risk . Typical process (delta hedge): 1. Choose an option model 2. Calibrate the model (using real price(s)) to estimate model parameters 3. Differentiate the model (with parameters now determined) at current point to determine delta hedge BUT: - fails to capture parameter dependence on underlying - does not minimize variance of hedge risk
  • 11. Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018 Practitioner's BS delta hedging for an option: 1. Assume that the underlying follows a BS underlying price model: ( )t t t tdS r q S dt S dW  
  • 12. Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018 Practitioner's BS delta hedging for an option: 1. Assume that the underlying follows a BS underlying price model: 2. Calibrate BS implied volatility from the market option price ( )t t t tdS r q S dt S dW   MKTV ( ; )BS MKTV S V 
  • 13. Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018 Practitioner's BS delta hedging for an option: 1. Assume that the underlying follows a BS underlying model: 2. Calibrate BS implied volatility from the market option price 3. Compute the BS delta using implied vol ( )t t t tdS r q S dt S dW    MKTV ( ; )BS MKTV S V  BSV S  
  • 14. Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018 0In Coleman et al (2001) we illustrated the dependence of on S
  • 15. Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018 Minimum Variance Hedging Goal: minimize option risk minimize variance (MV) in hedging error. Let : instantaneous change in underlying : instantaneous change in option value : position in underlying for a MV strategy Hedging error: MV delta hedging: dS dV MV MVdV dS min variance ( ) (1)MV MVdV dS 
  • 16. Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018 For example, Hull and White [2017] directly attack (1) by assuming Using market data to determine parameters a,b,c Hull and White approximate E( )BS BS MV V V S S             2 E( ) ( )BS BS a b c S S T       
  • 17. Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018 For example, Hull and White [] directly attack (1) by assuming Using market data to determine parameters a,b,c Hull and White approximate Improved results are obtained using this correction to BS-delta: E( )BS BS MV V V S S             2 E( ) ( )BS BS a b c S S T        2 ( ) ( ) BS BS BS BS MV a b c vega S T        
  • 18. Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018 Our new data-driven approach: Solve directly from the market data : no option models: use (standard) ML techniques directly min variance ( ) (1)MV MVdV dS 
  • 19. Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018 Our new approach: solve directly from the market data : no option models: use (standard) ML techniques directly min variance ( ) (1)MV MVdV dS  learn
  • 20. Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018 A Machine Learning Primer Given m training points: Where x: feature vector y: target (or outcome) A regularized kernel method learns a nonlinear function to capture the dependence between target y and feature vector x. is then used to ‘predict’ y for feature selection x 1 1{( , ),...,( , )}m mx y x y ( )f x ( )f x
  • 21. Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018 A Machine Learning Primer Given m training points: Where x: feature vector y: target (or outcome) A regularized kernel method learns a nonlinear function to capture the dependence between target y and feature vector x. is then used to ‘predict’ y for feature selection x Choose a positive definite kernel: e.g., 1 1{( , ),...,( , )}m mx y x y ( )f x ( )f x 2 2 2 ' 2 ( , ') x x k x x e    
  • 22. Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018 A Machine Learning Primer Given m training points: Where x: feature vector y: target (or outcome) A regularized kernel method learns a nonlinear function to capture the dependence between target y and feature vector x. is then used to ‘predict’ y for feature selection x Choose a positive definite kernel: e.g., A regularized regression problem: 1 1{( , ),...,( , )}m mx y x y ( )f x ( )f x 2 2 2 ' 2 ( , ') x x k x x e    
  • 23. Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018 A regularized (nonlinear) regression problem (to determine (learn) parameters that define ) : 2 1 1 min ( , ( )) , e.g., ( , ( )) ( ) m f i i i p i i i i L y f x f m L y f x y f x             Defined by choice of K f
  • 24. Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018 A regularized (nonlinear) regression problem: 2 1 1 min ( , ( )) , e.g., ( , ( )) ( ) m f i i i p i i i i L y f x f m L y f x y f x            
  • 25. Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018 A regularized (nonlinear) regression problem: where m-vector minimizes the pos def quadratic: 2 1 1 min ( , ( )) , e.g., ( , ( )) ( ) m f i i i p i i i i L y f x f m L y f x y f x             1 ( ) ( , ) m i i i f x k x x     2 1 1 1 1 min { ( ( , )) ( , )}m m m m m i j i j i j i j i j i j y k x x k x x            
  • 26. Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018 A regularized (nonlinear) regression problem: where m-vector minimizes the pos def quadratic: or 2 1 1 min ( , ( )) , e.g., ( , ( )) ( ) m f i i i p i i i i L y f x f m L y f x y f x             1 ( ) ( , ) m i i i f x k x x     2 1 1 1 1 min { ( ( , )) ( , )}m m m m m i j i j i j i j i j i j y k x x k x x             2 2 min { }, where ( , )T ij i jy K K K k x x     
  • 27. Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018 A regularized (nonlinear) regression problem: where m-vector minimizes the pos def quadratic: or or 2 1 1 min ( , ( )) , e.g., ( , ( )) ( ) m f i i i p i i i i L y f x f m L y f x y f x             1 ( ) ( , ) m i i i f x k x x     2 1 1 1 1 min { ( ( , )) ( , )}m m m m m i j i j i j i j i j i j y k x x k x x             2 2 min { }, where ( , )T ij i jy K K K k x x      1 ( )K I y    
  • 28. Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018 Recipe for determining ML model 1. Choose feature vector x , kernel k 2. Get data 3. Form m-by-m matrix 4. Determine (cross validation) 5. Solve ( , ), 1:i ix y i m ( ( , ))i jK k x x ( )K I y   
  • 29. Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018 Recipe for determining ML model 1. Choose feature vector x , kernel k 2. Get data 3. Form m-by-m matrix 4. Determine (cross validation) 5. Solve Prediction: ( , ), 1:i ix y i m ( ( , ))i jK k x x ( )K I y    1 ( ) ( , ) m pred i i i y x k x x   
  • 30. Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018 To apply to our problem: 1. What is feature vector x? 2. Kernel function k? 3. Data? 4. Choose And most importantly 
  • 31. Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018 To apply to our problem: 1. What is feature vector x? 2. Kernel function k? 3. Data? 4. Choose And most importantly, what is objective function:  2 1 1 min ( , ( )) m f i i i L y f x f m           min variance ( )MV MVdV dS  Key!
  • 32. Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018 Learn hedging function directly from the market using ML approach: let be a positive definite kernel where denotes change in (observed) market price Solution is ( )f x 22 1 1 min ( ( )) m f i i i i V S f x f m              t i i iV V V    1 ( ) ( , ) m i i i f x k x x    ( , ')k x x
  • 33. Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018 Learn hedging function directly from the market using ML approach: let be a positive definite kernel. where denotes change in (observed) market price Solution is Where solves the pos def. quadratic minimization: Features x = moneyness , time-to-expiry; ( )f x 22 1 1 min ( ( )) m f i i i i V S f x f m              t i i iV V V    1 ( ) ( , ) m i i i f x k x x    ( , ')k x x  2 1 1 1 1 min { ( ( ( , )) ( , )}m m m m m i i i i j i j i j i i i j V S k x x k x x               BS ( ) S strike
  • 34. Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018 Empirical Results Data: S&P 500 index option data from the OptionMetric Database data: January 2, 2004 to August 31, 2015
  • 35. Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018 Empirical Results Data: S&P 500 index option data from the OptionMetric Database data: January 2, 2004 to August 31, 2015 Methods compared: MV: Hull-White's minimum variance hedging based on formulation LVF: MV hedging using correction based on LVF analysis BS: implied volatility BS delta hedging SABR : MV hedging from SABR stochastic volatility. DKLSPL : direct learning a spline kernel hedging function
  • 36. Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018 Empirical Results Data: S&P 500 index option data from the OptionMetric Database data: January 2, 2004 to August 31, 2015 Methods compared: MV: Hull-White's minimum variance hedging based on formulation LVF: MV hedging using correction based on LVF analysis BS: implied volatility BS delta hedging SABR : MV hedging from SABR stochastic volatility. DKLSPL : direct learning a spline kernel hedging function Performance Measure: 2 1 2 1 ( ) ( ) m M i i i m BS i i i V S GAIN V S             
  • 37. Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018 Empirical Testing Data: S&P 500 index option data from the OptionMetric Database data: January 2, 2004 to August 31, 2015 Sliding window: 3 years data 1 mth-out-of sample learning model testing 9 buckets, 9 models
  • 38. Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018 9 buckets, 9 models
  • 39. Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018
  • 40. Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018
  • 41. Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018
  • 42. Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018 Concluding remarks We have proposed to learn the hedge function directly from market data (using ML techniques).
  • 43. Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018 Concluding remarks We have proposed to learn the hedge function directly from market data (using ML techniques). Empirical results show - proposed approach definitively outperforms existing MV hedge methods in daily hedging
  • 44. Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018 Concluding remarks We have proposed to learn the hedge function directly from market data (using ML techniques). Empirical results show - proposed approach definitively outperforms existing MV hedge methods in daily hedging - proposed approach definitively outperforms implied vol BS hedge in daily, weekly and monthly hedging
  • 45. Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018 Concluding remarks We have proposed to learn the hedge function directly from market data (using ML techniques). Empirical results show - proposed approach definitively outperforms existing MV hedge methods in daily hedging - proposed approach definitively outperforms implied vol BS hedge in daily, weekly and monthly hedging Question: What other important (predictive) problems in finance, traditionally solved with highly developed specialized finance models, are amenable to general data driven machine learning techniques?
  • 46. Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018 REFERENCES T. F. Coleman, Y. Kim, Y. Li, A. Verma, Dynamic hedging with a deterministic local volatility function model, The Journal of Risk 5 (2001) 63:89. J. Hull, A. White, Optimal delta hedging for options Journal of Banking & Finance, 82:180-190, 2017 G. Bakshi, C. Cao, Z. Chen, Empirical performance of alternative option pricing models, The Journal of Finance 52 (1997) 2003. S. Crepey, Delta-hedging vega risk, Quantitative Finance 4 (2004) 559{579. G. Bakshi, C. Cao, Z. Chen, The Journal of Finance 52 (1997) 2003{2049. K. P. R., R. Schenk-Hoppe, C.-O. Ewald, Risk minimization in stochastic volatility models: model risk and empirical performance, Quantitative Finance 9 (2009) 693{704. G. Bakshi, C. Cao, Z. Chen, The Journal of Finance 52 (1997) 2003. J. Hutchinson, A. Lo, T. Poggio. A nonparametric approach to pricing and hedging derivative securities via learning networks. The Journal of Finance. 49(3):851-889, 1994
  • 47. Thomas Coleman , University of Waterloo Machine Learning Fintech Conference 2.0. May 2, 2018