GEV-Canonical Regression for Accurate Binary Class Probability Estimation when One Class is Rare

Size: px
Start display at page:

Download "GEV-Canonical Regression for Accurate Binary Class Probability Estimation when One Class is Rare"

Transcription

1 GEV-Canonical Regression for Accurate Binary Class Probability Estimation when One Class is Rare ArpitAgarwal 1 HarikrishnaNarasimhan 1 ShivaramKalyanakrishnan 2 ShivaniAgarwal 1 1 Indian Institute of Science, Bangalore 2 Yahoo Labs, Bangalore

2 Binary Problems where One Class is Rare Fraud detection

3 Binary Problems where One Class is Rare Fraud detection Medical diagnosis

4 Binary Problems where One Class is Rare Fraud detection Medical diagnosis Webadvertising

5 Binary Problems where One Class is Rare + + +

6 Problem Setup Instance space, Label space Probability distribution on,

7 Problem Setup Instance space, Label space Probability distribution on, We are interested in settings where zzzzzzzzz

8 Problem Setup Instance space, Label space Probability distribution on, Goal:Given a training sample learn a good class probability estimation (CPE) model

9 Previous Approaches Weightingerrors on positive and negative examples differently (Provost, 2000; Japkowicz, 2000; Chawlaet al., 2004; Van Hulseet al., 2007; He & Garcia, 2009) Undersamplingmajority class to balance positive and negative examples (King & Zeng, 2001) Asymmetric `link function based on generalized extreme value (GEV) distribution (Wang & Dey, 2010; Calabrese & Osmetti, 2011)

10 Our Work We use tools from the theory of proper composite lossesto design a loss based on the GEV link termed GEV-canonical GEV-canonical loss is both flexible and convex We also propose the GEV-canonical regression algorithm for its minimization

11 Outline Proper Composite Loss Functions GEV-Canonical Loss Function & GEV-Canonical Regression Algorithm Experiments

12 Loss Functions for CPE A CPE loss function assigns a penalty for predicting when the true label is y

13 Loss Functions for CPE A CPE loss function assigns a penalty for predicting when the true label is y Can be defined by its partial losses and, given by

14 Proper Loss Functions A CPE loss function is proper if and strictly proper if the minimizer is unique

15 Example: Logarithmic Loss

16 Example: Logarithmic Loss Log loss is strictly proper

17 Link Functions Let A link function \psi:[0,1] V is any strictly increasing (and therefore invertible) function that maps probabilities in [0,1] to real-valued scores in

18 Example: LogitLink

19 Example: ProbitLink

20 Example: Complementary Log-Log Link

21 Proper Composite Loss Functions [Buja et al, 2005; Reid & Williamson, 2009, 2010] A loss function is said to be proper composite if a proper CPE loss and a link \psi:[0,1] s.t.

22 Canonical Proper Loss & Link Pairs [Buja et al, 2005; Reid & Williamson, 2009, 2010] For every link function there is a unique canonical proper loss function given by:

23 Canonical Proper Loss & Link Pairs [Buja et al, 2005; Reid & Williamson, 2009, 2010] For every link function there is a unique canonical proper loss function given by: The resulting proper composite losshas some nice properties, including convexity.

24 Example: Logistic Loss Log Loss + LogitLink = Logistic Loss

25 Example: Logistic Loss Log Loss + LogitLink = Logistic Loss Canonical pair

26 Outline Proper Composite Loss Functions GEV-Canonical Loss Function & GEV-Canonical Regression Algorithm Experiments

27 Generalized Extreme Value (GEV) Probability Distribution CDF of GEV distributionwith location parameter scale parameter and shape parameter : Used for modeling rare events in statistics

28 GEV Link Family (Parameterized by -----)

29 GEV-Log Loss Effectively Used in (Wang & Dey, 2010; Calabrese & Osmetti, 2011) Log Loss + GEV Link = GEV-Log Loss

30 GEV-Log Loss Effectively Used in (Wang & Dey, 2010; Calabrese & Osmetti, 2011) Log Loss + GEV Link = GEV-Log Loss

31 GEV-Log Loss Effectively Used in (Wang & Dey, 2010; Calabrese & Osmetti, 2011) Log Loss + GEV Link = GEV-Log Loss NOT a canonical pair; results in non-convex loss

32 Canonical Proper Loss for GEV Link

33 GEV-Canonical Loss (Canonical Loss) +GEV Link = GEV-Canonical Loss

34 GEV-Canonical Loss (Canonical Loss) +GEV Link = GEV-Canonical Loss Canonical pair by construction; results in convex loss!

35 GEV-Canonical Loss (Canonical Loss) +GEV Link = GEV-Canonical Loss Canonical pair by construction; results in convex loss!

36 GEV-Canonical Loss Can be tailoredfor the problem of CPE for varying degrees of rarity Not available in closed form. But, the gradient and Hessian are available in closed form Can be efficiently minimized using IRLS type algorithm. We term this GEV-canonical regression

37 GEV-Canonical Regression

38 Outline Proper Composite Loss Functions GEV-Canonical Loss Function & GEV-Canonical Regression Algorithm Experiments

39 Experiments We have conducted experiments with both synthetic and real data Parameter selected using a validation set. Results averaged over 10 experiments.

40 Experiments with Synthetic Data Evaluation Metric: Root Mean Square Error (RMSE) Dataset 1 : p= Dataset 2 : p= Dataset 3 : p= 0.095

41 Experiments with Real Data Experimented with 12 UCI data sets Evaluation Metric: Brier Score (Brier, 1950)

42 Summary

43 Conclusion and Future Work Proposed GEV-canonical regression algorithm using convex GEV-canonical lossfor the problem of CPE when one class is rare Future directions: extensions to large scale data statistical guarantees

A Joint Credit Scoring Model for Peer-to-Peer Lending and Credit Bureau

A Joint Credit Scoring Model for Peer-to-Peer Lending and Credit Bureau A Joint Credit Scoring Model for Peer-to-Peer Lending and Credit Bureau Credit Research Centre and University of Edinburgh raffaella.calabrese@ed.ac.uk joint work with Silvia Osmetti and Luca Zanin Credit

More information

Frequency Distribution Models 1- Probability Density Function (PDF)

Frequency Distribution Models 1- Probability Density Function (PDF) Models 1- Probability Density Function (PDF) What is a PDF model? A mathematical equation that describes the frequency curve or probability distribution of a data set. Why modeling? It represents and summarizes

More information

Investing through Economic Cycles with Ensemble Machine Learning Algorithms

Investing through Economic Cycles with Ensemble Machine Learning Algorithms Investing through Economic Cycles with Ensemble Machine Learning Algorithms Thomas Raffinot Silex Investment Partners Big Data in Finance Conference Thomas Raffinot (Silex-IP) Economic Cycles-Machine Learning

More information

CPSC 540: Machine Learning

CPSC 540: Machine Learning CPSC 540: Machine Learning Monte Carlo Methods Mark Schmidt University of British Columbia Winter 2019 Last Time: Markov Chains We can use Markov chains for density estimation, d p(x) = p(x 1 ) p(x }{{}

More information

Laplace approximation

Laplace approximation NPFL108 Bayesian inference Approximate Inference Laplace approximation Filip Jurčíček Institute of Formal and Applied Linguistics Charles University in Prague Czech Republic Home page: http://ufal.mff.cuni.cz/~jurcicek

More information

Introduction to Algorithmic Trading Strategies Lecture 8

Introduction to Algorithmic Trading Strategies Lecture 8 Introduction to Algorithmic Trading Strategies Lecture 8 Risk Management Haksun Li haksun.li@numericalmethod.com www.numericalmethod.com Outline Value at Risk (VaR) Extreme Value Theory (EVT) References

More information

Package ensemblemos. March 22, 2018

Package ensemblemos. March 22, 2018 Type Package Title Ensemble Model Output Statistics Version 0.8.2 Date 2018-03-21 Package ensemblemos March 22, 2018 Author RA Yuen, Sandor Baran, Chris Fraley, Tilmann Gneiting, Sebastian Lerch, Michael

More information

CPSC 540: Machine Learning

CPSC 540: Machine Learning CPSC 540: Machine Learning Monte Carlo Methods Mark Schmidt University of British Columbia Winter 2018 Last Time: Markov Chains We can use Markov chains for density estimation, p(x) = p(x 1 ) }{{} d p(x

More information

ECS171: Machine Learning

ECS171: Machine Learning ECS171: Machine Learning Lecture 15: Tree-based Algorithms Cho-Jui Hsieh UC Davis March 7, 2018 Outline Decision Tree Random Forest Gradient Boosted Decision Tree (GBDT) Decision Tree Each node checks

More information

Agricultural and Applied Economics 637 Applied Econometrics II

Agricultural and Applied Economics 637 Applied Econometrics II Agricultural and Applied Economics 637 Applied Econometrics II Assignment I Using Search Algorithms to Determine Optimal Parameter Values in Nonlinear Regression Models (Due: February 3, 2015) (Note: Make

More information

Estimation of a Ramsay-Curve IRT Model using the Metropolis-Hastings Robbins-Monro Algorithm

Estimation of a Ramsay-Curve IRT Model using the Metropolis-Hastings Robbins-Monro Algorithm 1 / 34 Estimation of a Ramsay-Curve IRT Model using the Metropolis-Hastings Robbins-Monro Algorithm Scott Monroe & Li Cai IMPS 2012, Lincoln, Nebraska Outline 2 / 34 1 Introduction and Motivation 2 Review

More information

Overview. Family of powers and roots

Overview. Family of powers and roots 4. Transformations Overview.................................................................. 2 Family of powers and roots...................................................... 3 Family of powers and roots......................................................

More information

1 Overview. 2 The Gradient Descent Algorithm. AM 221: Advanced Optimization Spring 2016

1 Overview. 2 The Gradient Descent Algorithm. AM 221: Advanced Optimization Spring 2016 AM 22: Advanced Optimization Spring 206 Prof. Yaron Singer Lecture 9 February 24th Overview In the previous lecture we reviewed results from multivariate calculus in preparation for our journey into convex

More information

Intro to GLM Day 2: GLM and Maximum Likelihood

Intro to GLM Day 2: GLM and Maximum Likelihood Intro to GLM Day 2: GLM and Maximum Likelihood Federico Vegetti Central European University ECPR Summer School in Methods and Techniques 1 / 32 Generalized Linear Modeling 3 steps of GLM 1. Specify the

More information

Introduction to POL 217

Introduction to POL 217 Introduction to POL 217 Brad Jones 1 1 Department of Political Science University of California, Davis January 9, 2007 Topics of Course Outline Models for Categorical Data. Topics of Course Models for

More information

Laws of probabilities in efficient markets

Laws of probabilities in efficient markets Laws of probabilities in efficient markets Vladimir Vovk Department of Computer Science Royal Holloway, University of London Fifth Workshop on Game-Theoretic Probability and Related Topics 15 November

More information

Predictive Modeling Cross Selling of Home Loans to Credit Card Customers

Predictive Modeling Cross Selling of Home Loans to Credit Card Customers PAKDD COMPETITION 2007 Predictive Modeling Cross Selling of Home Loans to Credit Card Customers Hualin Wang 1 Amy Yu 1 Kaixia Zhang 1 800 Tech Center Drive Gahanna, Ohio 43230, USA April 11, 2007 1 Outline

More information

Learning from Data: Learning Logistic Regressors

Learning from Data: Learning Logistic Regressors Learning from Data: Learning Logistic Regressors November 1, 2005 http://www.anc.ed.ac.uk/ amos/lfd/ Learning Logistic Regressors P(t x) = σ(w T x + b). Want to learn w and b using training data. As before:

More information

The Use of Artificial Neural Network for Forecasting of FTSE Bursa Malaysia KLCI Stock Price Index

The Use of Artificial Neural Network for Forecasting of FTSE Bursa Malaysia KLCI Stock Price Index The Use of Artificial Neural Network for Forecasting of FTSE Bursa Malaysia KLCI Stock Price Index Soleh Ardiansyah 1, Mazlina Abdul Majid 2, JasniMohamad Zain 2 Faculty of Computer System and Software

More information

Finding optimal arbitrage opportunities using a quantum annealer

Finding optimal arbitrage opportunities using a quantum annealer Finding optimal arbitrage opportunities using a quantum annealer White Paper Finding optimal arbitrage opportunities using a quantum annealer Gili Rosenberg Abstract We present two formulations for finding

More information

Decision Trees An Early Classifier

Decision Trees An Early Classifier An Early Classifier Jason Corso SUNY at Buffalo January 19, 2012 J. Corso (SUNY at Buffalo) Trees January 19, 2012 1 / 33 Introduction to Non-Metric Methods Introduction to Non-Metric Methods We cover

More information

MANAGEMENT SCIENCE doi /mnsc ec

MANAGEMENT SCIENCE doi /mnsc ec MANAGEMENT SCIENCE doi 10.1287/mnsc.1100.1159ec e-companion ONLY AVAILABLE IN ELECTRONIC FORM informs 2010 INFORMS Electronic Companion Quality Management and Job Quality: How the ISO 9001 Standard for

More information

The University of Chicago, Booth School of Business Business 41202, Spring Quarter 2017, Mr. Ruey S. Tsay. Solutions to Final Exam

The University of Chicago, Booth School of Business Business 41202, Spring Quarter 2017, Mr. Ruey S. Tsay. Solutions to Final Exam The University of Chicago, Booth School of Business Business 41202, Spring Quarter 2017, Mr. Ruey S. Tsay Solutions to Final Exam Problem A: (40 points) Answer briefly the following questions. 1. Describe

More information

Predicting stock prices for large-cap technology companies

Predicting stock prices for large-cap technology companies Predicting stock prices for large-cap technology companies 15 th December 2017 Ang Li (al171@stanford.edu) Abstract The goal of the project is to predict price changes in the future for a given stock.

More information

Section 6.5. The Central Limit Theorem

Section 6.5. The Central Limit Theorem Section 6.5 The Central Limit Theorem Idea Will allow us to combine the theory from 6.4 (sampling distribution idea) with our central limit theorem and that will allow us the do hypothesis testing in the

More information

DEM Working Paper Series. Estimating bank default with generalised extreme value models

DEM Working Paper Series. Estimating bank default with generalised extreme value models ISSN: 2281-1346 Department of Economics and Management DEM Working Paper Series Estimating bank default with generalised extreme value models Raffaella Calabrese (Università Bicocca) Paolo Giudici (Università

More information

Valencia. Keywords: Conditional volatility, backpropagation neural network, GARCH in Mean MSC 2000: 91G10, 91G70

Valencia. Keywords: Conditional volatility, backpropagation neural network, GARCH in Mean MSC 2000: 91G10, 91G70 Int. J. Complex Systems in Science vol. 2(1) (2012), pp. 21 26 Estimating returns and conditional volatility: a comparison between the ARMA-GARCH-M Models and the Backpropagation Neural Network Fernando

More information

Questions 3-6 are each weighted twice as much as each of the other questions.

Questions 3-6 are each weighted twice as much as each of the other questions. Mathematics 107 Professor Alan H. Stein December 1, 005 SOLUTIONS Final Examination Questions 3-6 are each weighted twice as much as each of the other questions. 1. A savings account is opened with a deposit

More information

Session 5. Predictive Modeling in Life Insurance

Session 5. Predictive Modeling in Life Insurance SOA Predictive Analytics Seminar Hong Kong 29 Aug. 2018 Hong Kong Session 5 Predictive Modeling in Life Insurance Jingyi Zhang, Ph.D Predictive Modeling in Life Insurance JINGYI ZHANG PhD Scientist Global

More information

Ph.D. Preliminary Examination MICROECONOMIC THEORY Applied Economics Graduate Program August 2017

Ph.D. Preliminary Examination MICROECONOMIC THEORY Applied Economics Graduate Program August 2017 Ph.D. Preliminary Examination MICROECONOMIC THEORY Applied Economics Graduate Program August 2017 The time limit for this exam is four hours. The exam has four sections. Each section includes two questions.

More information

International Journal of Computer Engineering and Applications, Volume XII, Issue II, Feb. 18, ISSN

International Journal of Computer Engineering and Applications, Volume XII, Issue II, Feb. 18,   ISSN Volume XII, Issue II, Feb. 18, www.ijcea.com ISSN 31-3469 AN INVESTIGATION OF FINANCIAL TIME SERIES PREDICTION USING BACK PROPAGATION NEURAL NETWORKS K. Jayanthi, Dr. K. Suresh 1 Department of Computer

More information

Non linearity issues in PD modelling. Amrita Juhi Lucas Klinkers

Non linearity issues in PD modelling. Amrita Juhi Lucas Klinkers Non linearity issues in PD modelling Amrita Juhi Lucas Klinkers May 2017 Content Introduction Identifying non-linearity Causes of non-linearity Performance 2 Content Introduction Identifying non-linearity

More information

Tests for the Odds Ratio in a Matched Case-Control Design with a Binary X

Tests for the Odds Ratio in a Matched Case-Control Design with a Binary X Chapter 156 Tests for the Odds Ratio in a Matched Case-Control Design with a Binary X Introduction This procedure calculates the power and sample size necessary in a matched case-control study designed

More information

-divergences and Monte Carlo methods

-divergences and Monte Carlo methods -divergences and Monte Carlo methods Summary - english version Ph.D. candidate OLARIU Emanuel Florentin Advisor Professor LUCHIAN Henri This thesis broadly concerns the use of -divergences mainly for variance

More information

Wage Determinants Analysis by Quantile Regression Tree

Wage Determinants Analysis by Quantile Regression Tree Communications of the Korean Statistical Society 2012, Vol. 19, No. 2, 293 301 DOI: http://dx.doi.org/10.5351/ckss.2012.19.2.293 Wage Determinants Analysis by Quantile Regression Tree Youngjae Chang 1,a

More information

Available online at ScienceDirect. Procedia Computer Science 89 (2016 )

Available online at  ScienceDirect. Procedia Computer Science 89 (2016 ) Available online at www.sciencedirect.com ScienceDirect Procedia Computer Science 89 (2016 ) 441 449 Twelfth International Multi-Conference on Information Processing-2016 (IMCIP-2016) Prediction Models

More information

Mongolia s TOP-20 Index Risk Analysis, Pt. 3

Mongolia s TOP-20 Index Risk Analysis, Pt. 3 Mongolia s TOP-20 Index Risk Analysis, Pt. 3 Federico M. Massari March 12, 2017 In the third part of our risk report on TOP-20 Index, Mongolia s main stock market indicator, we focus on modelling the right

More information

Description Quick start Menu Syntax Options Remarks and examples Stored results Methods and formulas Acknowledgment References Also see

Description Quick start Menu Syntax Options Remarks and examples Stored results Methods and formulas Acknowledgment References Also see Title stata.com tssmooth shwinters Holt Winters seasonal smoothing Description Quick start Menu Syntax Options Remarks and examples Stored results Methods and formulas Acknowledgment References Also see

More information

Structured RAY Risk-Adjusted Yield for Securitizations and Loan Pools

Structured RAY Risk-Adjusted Yield for Securitizations and Loan Pools Structured RAY Risk-Adjusted Yield for Securitizations and Loan Pools Market Yields for Mortgage Loans The mortgage loans over which the R and D scoring occurs have risk characteristics that investors

More information

,,, be any other strategy for selling items. It yields no more revenue than, based on the

,,, be any other strategy for selling items. It yields no more revenue than, based on the ONLINE SUPPLEMENT Appendix 1: Proofs for all Propositions and Corollaries Proof of Proposition 1 Proposition 1: For all 1,2,,, if, is a non-increasing function with respect to (henceforth referred to as

More information

Monotone, Convex and Extrema

Monotone, Convex and Extrema Monotone Functions Function f is called monotonically increasing, if Chapter 8 Monotone, Convex and Extrema x x 2 f (x ) f (x 2 ) It is called strictly monotonically increasing, if f (x 2) f (x ) x < x

More information

Financial Risk Forecasting Chapter 9 Extreme Value Theory

Financial Risk Forecasting Chapter 9 Extreme Value Theory Financial Risk Forecasting Chapter 9 Extreme Value Theory Jon Danielsson 2017 London School of Economics To accompany Financial Risk Forecasting www.financialriskforecasting.com Published by Wiley 2011

More information

What can we do with numerical optimization?

What can we do with numerical optimization? Optimization motivation and background Eddie Wadbro Introduction to PDE Constrained Optimization, 2016 February 15 16, 2016 Eddie Wadbro, Introduction to PDE Constrained Optimization, February 15 16, 2016

More information

ALGORITHMIC TRADING STRATEGIES IN PYTHON

ALGORITHMIC TRADING STRATEGIES IN PYTHON 7-Course Bundle In ALGORITHMIC TRADING STRATEGIES IN PYTHON Learn to use 15+ trading strategies including Statistical Arbitrage, Machine Learning, Quantitative techniques, Forex valuation methods, Options

More information

9. Logit and Probit Models For Dichotomous Data

9. Logit and Probit Models For Dichotomous Data Sociology 740 John Fox Lecture Notes 9. Logit and Probit Models For Dichotomous Data Copyright 2014 by John Fox Logit and Probit Models for Dichotomous Responses 1 1. Goals: I To show how models similar

More information

A case study on using generalized additive models to fit credit rating scores

A case study on using generalized additive models to fit credit rating scores Int. Statistical Inst.: Proc. 58th World Statistical Congress, 2011, Dublin (Session CPS071) p.5683 A case study on using generalized additive models to fit credit rating scores Müller, Marlene Beuth University

More information

PASS Sample Size Software

PASS Sample Size Software Chapter 850 Introduction Cox proportional hazards regression models the relationship between the hazard function λ( t X ) time and k covariates using the following formula λ log λ ( t X ) ( t) 0 = β1 X1

More information

Pattern Recognition Chapter 5: Decision Trees

Pattern Recognition Chapter 5: Decision Trees Pattern Recognition Chapter 5: Decision Trees Asst. Prof. Dr. Chumphol Bunkhumpornpat Department of Computer Science Faculty of Science Chiang Mai University Learning Objectives How decision trees are

More information

Investigation and comparison of sampling properties of L-moments and conventional moments

Investigation and comparison of sampling properties of L-moments and conventional moments Journal of Hydrology 218 (1999) 13 34 Investigation and comparison of sampling properties of L-moments and conventional moments A. Sankarasubramanian 1, K. Srinivasan* Department of Civil Engineering,

More information

Technical Note: Multi-Product Pricing Under the Generalized Extreme Value Models with Homogeneous Price Sensitivity Parameters

Technical Note: Multi-Product Pricing Under the Generalized Extreme Value Models with Homogeneous Price Sensitivity Parameters Technical Note: Multi-Product Pricing Under the Generalized Extreme Value Models with Homogeneous Price Sensitivity Parameters Heng Zhang, Paat Rusmevichientong Marshall School of Business, University

More information

Econometric Models of Expenditure

Econometric Models of Expenditure Econometric Models of Expenditure Benjamin M. Craig University of Arizona ISPOR Educational Teleconference October 28, 2005 1 Outline Overview of Expenditure Estimator Selection Two problems Two mistakes

More information

CSC 411: Lecture 08: Generative Models for Classification

CSC 411: Lecture 08: Generative Models for Classification CSC 411: Lecture 08: Generative Models for Classification Richard Zemel, Raquel Urtasun and Sanja Fidler University of Toronto Zemel, Urtasun, Fidler (UofT) CSC 411: 08-Generative Models 1 / 23 Today Classification

More information

CS 475 Machine Learning: Final Project Dual-Form SVM for Predicting Loan Defaults

CS 475 Machine Learning: Final Project Dual-Form SVM for Predicting Loan Defaults CS 475 Machine Learning: Final Project Dual-Form SVM for Predicting Loan Defaults Kevin Rowland Johns Hopkins University 3400 N. Charles St. Baltimore, MD 21218, USA krowlan3@jhu.edu Edward Schembor Johns

More information

WC-5 Just How Credible Is That Employer? Exploring GLMs and Multilevel Modeling for NCCI s Excess Loss Factor Methodology

WC-5 Just How Credible Is That Employer? Exploring GLMs and Multilevel Modeling for NCCI s Excess Loss Factor Methodology Antitrust Notice The Casualty Actuarial Society is committed to adhering strictly to the letter and spirit of the antitrust laws. Seminars conducted under the auspices of the CAS are designed solely to

More information

Department of Economics ECO 204 Microeconomic Theory for Commerce Test 2

Department of Economics ECO 204 Microeconomic Theory for Commerce Test 2 Department of Economics ECO 204 Microeconomic Theory for Commerce 2013-2014 Test 2 IMPORTANT NOTES: Proceed with this exam only after getting the go-ahead from the Instructor or the proctor Do not leave

More information

The University of Chicago, Booth School of Business Business 41202, Spring Quarter 2009, Mr. Ruey S. Tsay. Solutions to Final Exam

The University of Chicago, Booth School of Business Business 41202, Spring Quarter 2009, Mr. Ruey S. Tsay. Solutions to Final Exam The University of Chicago, Booth School of Business Business 41202, Spring Quarter 2009, Mr. Ruey S. Tsay Solutions to Final Exam Problem A: (42 pts) Answer briefly the following questions. 1. Questions

More information

Dependence Structure and Extreme Comovements in International Equity and Bond Markets

Dependence Structure and Extreme Comovements in International Equity and Bond Markets Dependence Structure and Extreme Comovements in International Equity and Bond Markets René Garcia Edhec Business School, Université de Montréal, CIRANO and CIREQ Georges Tsafack Suffolk University Measuring

More information

A Skewed Truncated Cauchy Uniform Distribution and Its Moments

A Skewed Truncated Cauchy Uniform Distribution and Its Moments Modern Applied Science; Vol. 0, No. 7; 206 ISSN 93-844 E-ISSN 93-852 Published by Canadian Center of Science and Education A Skewed Truncated Cauchy Uniform Distribution and Its Moments Zahra Nazemi Ashani,

More information

INSTITUTE OF ACTUARIES OF INDIA

INSTITUTE OF ACTUARIES OF INDIA INSTITUTE OF ACTUARIES OF INDIA EXAMINATIONS 27 th May, 2014 Subject SA3 General Insurance Time allowed: Three hours (14.45* - 18.00 Hours) Total Marks: 100 INSTRUCTIONS TO THE CANDIDATES 1. Please read

More information

A comment on Christoffersen, Jacobs and Ornthanalai (2012), Dynamic jump intensities and risk premiums: Evidence from S&P500 returns and options

A comment on Christoffersen, Jacobs and Ornthanalai (2012), Dynamic jump intensities and risk premiums: Evidence from S&P500 returns and options A comment on Christoffersen, Jacobs and Ornthanalai (2012), Dynamic jump intensities and risk premiums: Evidence from S&P500 returns and options Garland Durham 1 John Geweke 2 Pulak Ghosh 3 February 25,

More information

Measuring Inverse Demand Systems and Consumer Welfare. Kuo S. Huang

Measuring Inverse Demand Systems and Consumer Welfare. Kuo S. Huang 1 Measuring Inverse Demand Systems and Consumer Welfare Kuo S. Huang Economic Research Service U.S. Department of Agriculture Washington, DC 20036-5831 Poster prepared for presentation at the Agricultural

More information

Using Halton Sequences. in Random Parameters Logit Models

Using Halton Sequences. in Random Parameters Logit Models Journal of Statistical and Econometric Methods, vol.5, no.1, 2016, 59-86 ISSN: 1792-6602 (print), 1792-6939 (online) Scienpress Ltd, 2016 Using Halton Sequences in Random Parameters Logit Models Tong Zeng

More information

Data utility metrics and disclosure risk analysis for public use files

Data utility metrics and disclosure risk analysis for public use files Data utility metrics and disclosure risk analysis for public use files Specific Grant Agreement Production of Public Use Files for European microdata Work Package 3 - Deliverable D3.1 October 2015 This

More information

1 Excess burden of taxation

1 Excess burden of taxation 1 Excess burden of taxation 1. In a competitive economy without externalities (and with convex preferences and production technologies) we know from the 1. Welfare Theorem that there exists a decentralized

More information

: Corruption Lecture 2

: Corruption Lecture 2 14.75 : Corruption Lecture 2 Ben Olken Olken () Corruption Lecture 2 1 / 3 Outline Do we care? Magnitude and effi ciency costs The corrupt offi cial s decision problem Balancing risks, rents, and incentives

More information

Wide and Deep Learning for Peer-to-Peer Lending

Wide and Deep Learning for Peer-to-Peer Lending Wide and Deep Learning for Peer-to-Peer Lending Kaveh Bastani 1 *, Elham Asgari 2, Hamed Namavari 3 1 Unifund CCR, LLC, Cincinnati, OH 2 Pamplin College of Business, Virginia Polytechnic Institute, Blacksburg,

More information

Towards Developing Synthetic Datasets for the Economic Census

Towards Developing Synthetic Datasets for the Economic Census Towards Developing Synthetic Datasets for the Economic Census Katherine Jenny Thompson* Economic Statistical Methods Division U.S. Census Bureau Hang Kim University of Cincinnati *The views expressed in

More information

Model Paper Statistics Objective. Paper Code Time Allowed: 20 minutes

Model Paper Statistics Objective. Paper Code Time Allowed: 20 minutes Model Paper Statistics Objective Intermediate Part I (11 th Class) Examination Session 2012-2013 and onward Total marks: 17 Paper Code Time Allowed: 20 minutes Note:- You have four choices for each objective

More information

A Bayesian Control Chart for the Coecient of Variation in the Case of Pooled Samples

A Bayesian Control Chart for the Coecient of Variation in the Case of Pooled Samples A Bayesian Control Chart for the Coecient of Variation in the Case of Pooled Samples R van Zyl a,, AJ van der Merwe b a PAREXEL International, Bloemfontein, South Africa b University of the Free State,

More information

Review. ESD.260 Fall 2003

Review. ESD.260 Fall 2003 Review ESD.260 Fall 2003 1 Demand Forecasting 2 Accuracy and Bias Measures 1. Forecast Error: e t = D t -F t 2. Mean Deviation: MD = 3. Mean Absolute Deviation 4. Mean Squared Error: 5. Root Mean Squared

More information

Maximum Likelihood Estimation Richard Williams, University of Notre Dame, https://www3.nd.edu/~rwilliam/ Last revised January 13, 2018

Maximum Likelihood Estimation Richard Williams, University of Notre Dame, https://www3.nd.edu/~rwilliam/ Last revised January 13, 2018 Maximum Likelihood Estimation Richard Williams, University of otre Dame, https://www3.nd.edu/~rwilliam/ Last revised January 3, 208 [This handout draws very heavily from Regression Models for Categorical

More information

International Journal of Computer Science Trends and Technology (IJCST) Volume 5 Issue 2, Mar Apr 2017

International Journal of Computer Science Trends and Technology (IJCST) Volume 5 Issue 2, Mar Apr 2017 RESEARCH ARTICLE Stock Selection using Principal Component Analysis with Differential Evolution Dr. Balamurugan.A [1], Arul Selvi. S [2], Syedhussian.A [3], Nithin.A [4] [3] & [4] Professor [1], Assistant

More information

Lecture 10: Alternatives to OLS with limited dependent variables, part 1. PEA vs APE Logit/Probit

Lecture 10: Alternatives to OLS with limited dependent variables, part 1. PEA vs APE Logit/Probit Lecture 10: Alternatives to OLS with limited dependent variables, part 1 PEA vs APE Logit/Probit PEA vs APE PEA: partial effect at the average The effect of some x on y for a hypothetical case with sample

More information

Profit-based Logistic Regression: A Case Study in Credit Card Fraud Detection

Profit-based Logistic Regression: A Case Study in Credit Card Fraud Detection Profit-based Logistic Regression: A Case Study in Credit Card Fraud Detection Azamat Kibekbaev, Ekrem Duman Industrial Engineering Department Özyeğin University Istanbul, Turkey E-mail: kibekbaev.azamat@ozu.edu.tr,

More information

A Comparison of Universal and Mean-Variance Efficient Portfolios p. 1/28

A Comparison of Universal and Mean-Variance Efficient Portfolios p. 1/28 A Comparison of Universal and Mean-Variance Efficient Portfolios Shane M. Haas Research Laboratory of Electronics, and Laboratory for Information and Decision Systems Massachusetts Institute of Technology

More information

NOTES ON THE BANK OF ENGLAND OPTION IMPLIED PROBABILITY DENSITY FUNCTIONS

NOTES ON THE BANK OF ENGLAND OPTION IMPLIED PROBABILITY DENSITY FUNCTIONS 1 NOTES ON THE BANK OF ENGLAND OPTION IMPLIED PROBABILITY DENSITY FUNCTIONS Options are contracts used to insure against or speculate/take a view on uncertainty about the future prices of a wide range

More information

GENERALIZED PARETO DISTRIBUTION FOR FLOOD FREQUENCY ANALYSIS

GENERALIZED PARETO DISTRIBUTION FOR FLOOD FREQUENCY ANALYSIS GENERALIZED PARETO DISTRIBUTION FOR FLOOD FREQUENCY ANALYSIS by SAAD NAMED SAAD MOHARRAM Department of Civil Engineering THESIS SUBMITTED IN FULFILMENT OF THE REQUIREMENTS OF THE DEGREE OF DOCTOR OF PHILOSOPHY

More information

Decision Trees with Minimum Average Depth for Sorting Eight Elements

Decision Trees with Minimum Average Depth for Sorting Eight Elements Decision Trees with Minimum Average Depth for Sorting Eight Elements Hassan AbouEisha, Igor Chikalov, Mikhail Moshkov Computer, Electrical and Mathematical Sciences and Engineering Division, King Abdullah

More information

Gradient Boosting Trees: theory and applications

Gradient Boosting Trees: theory and applications Gradient Boosting Trees: theory and applications Dmitry Efimov November 05, 2016 Outline Decision trees Boosting Boosting trees Metaparameters and tuning strategies How-to-use remarks Regression tree True

More information

Steven Heston: Recovering the Variance Premium. Discussion by Jaroslav Borovička November 2017

Steven Heston: Recovering the Variance Premium. Discussion by Jaroslav Borovička November 2017 Steven Heston: Recovering the Variance Premium Discussion by Jaroslav Borovička November 2017 WHAT IS THE RECOVERY PROBLEM? Using observed cross-section(s) of prices (of Arrow Debreu securities), infer

More information

Chapter 6. Transformation of Variables

Chapter 6. Transformation of Variables 6.1 Chapter 6. Transformation of Variables 1. Need for transformation 2. Power transformations: Transformation to achieve linearity Transformation to stabilize variance Logarithmic transformation MACT

More information

Square Grid Benchmarks for Source-Terminal Network Reliability Estimation

Square Grid Benchmarks for Source-Terminal Network Reliability Estimation Square Grid Benchmarks for Source-Terminal Network Reliability Estimation Roger Paredes Leonardo Duenas-Osorio Rice University, Houston TX, USA. 03/2018 This document describes a synthetic benchmark data

More information

The Range, the Inter Quartile Range (or IQR), and the Standard Deviation (which we usually denote by a lower case s).

The Range, the Inter Quartile Range (or IQR), and the Standard Deviation (which we usually denote by a lower case s). We will look the three common and useful measures of spread. The Range, the Inter Quartile Range (or IQR), and the Standard Deviation (which we usually denote by a lower case s). 1 Ameasure of the center

More information

Lasso and Ridge Quantile Regression using Cross Validation to Estimate Extreme Rainfall

Lasso and Ridge Quantile Regression using Cross Validation to Estimate Extreme Rainfall Global Journal of Pure and Applied Mathematics. ISSN 0973-1768 Volume 12, Number 3 (2016), pp. 3305 3314 Research India Publications http://www.ripublication.com/gjpam.htm Lasso and Ridge Quantile Regression

More information

SELECTION BIAS REDUCTION IN CREDIT SCORING MODELS

SELECTION BIAS REDUCTION IN CREDIT SCORING MODELS SELECTION BIAS REDUCTION IN CREDIT SCORING MODELS Josef Ditrich Abstract Credit risk refers to the potential of the borrower to not be able to pay back to investors the amount of money that was loaned.

More information

Clustering Based Peer Selection with Financial Ratios. Kexing Ding Lucas Hoogduin Xuan Peng Miklos A. Vasarhelyi Yunsen Wang

Clustering Based Peer Selection with Financial Ratios. Kexing Ding Lucas Hoogduin Xuan Peng Miklos A. Vasarhelyi Yunsen Wang Clustering Based Peer Selection with Financial Ratios Kexing Ding Lucas Hoogduin Xuan Peng Miklos A. Vasarhelyi Yunsen Wang Introduction Academic research and practical models use anomaly detection strategies.

More information

1 Bayesian Bias Correction Model

1 Bayesian Bias Correction Model 1 Bayesian Bias Correction Model Assuming that n iid samples {X 1,...,X n }, were collected from a normal population with mean µ and variance σ 2. The model likelihood has the form, P( X µ, σ 2, T n >

More information

Multi-Armed Bandit, Dynamic Environments and Meta-Bandits

Multi-Armed Bandit, Dynamic Environments and Meta-Bandits Multi-Armed Bandit, Dynamic Environments and Meta-Bandits C. Hartland, S. Gelly, N. Baskiotis, O. Teytaud and M. Sebag Lab. of Computer Science CNRS INRIA Université Paris-Sud, Orsay, France Abstract This

More information

Non-linearities in Simple Regression

Non-linearities in Simple Regression Non-linearities in Simple Regression 1. Eample: Monthly Earnings and Years of Education In this tutorial, we will focus on an eample that eplores the relationship between total monthly earnings and years

More information

Generalized MLE per Martins and Stedinger

Generalized MLE per Martins and Stedinger Generalized MLE per Martins and Stedinger Martins ES and Stedinger JR. (March 2000). Generalized maximum-likelihood generalized extreme-value quantile estimators for hydrologic data. Water Resources Research

More information

Point-Biserial and Biserial Correlations

Point-Biserial and Biserial Correlations Chapter 302 Point-Biserial and Biserial Correlations Introduction This procedure calculates estimates, confidence intervals, and hypothesis tests for both the point-biserial and the biserial correlations.

More information

CS 237: Probability in Computing

CS 237: Probability in Computing CS 237: Probability in Computing Wayne Snyder Computer Science Department Boston University Lecture 10: o Cumulative Distribution Functions o Standard Deviations Bernoulli Binomial Geometric Cumulative

More information

Hierarchical Generalized Linear Models. Measurement Incorporated Hierarchical Linear Models Workshop

Hierarchical Generalized Linear Models. Measurement Incorporated Hierarchical Linear Models Workshop Hierarchical Generalized Linear Models Measurement Incorporated Hierarchical Linear Models Workshop Hierarchical Generalized Linear Models So now we are moving on to the more advanced type topics. To begin

More information

Optimal Window Selection for Forecasting in The Presence of Recent Structural Breaks

Optimal Window Selection for Forecasting in The Presence of Recent Structural Breaks Optimal Window Selection for Forecasting in The Presence of Recent Structural Breaks Yongli Wang University of Leicester Econometric Research in Finance Workshop on 15 September 2017 SGH Warsaw School

More information

Categorical Outcomes. Statistical Modelling in Stata: Categorical Outcomes. R by C Table: Example. Nominal Outcomes. Mark Lunt.

Categorical Outcomes. Statistical Modelling in Stata: Categorical Outcomes. R by C Table: Example. Nominal Outcomes. Mark Lunt. Categorical Outcomes Statistical Modelling in Stata: Categorical Outcomes Mark Lunt Arthritis Research UK Epidemiology Unit University of Manchester Nominal Ordinal 28/11/2017 R by C Table: Example Categorical,

More information

Role of soft computing techniques in predicting stock market direction

Role of soft computing techniques in predicting stock market direction REVIEWS Role of soft computing techniques in predicting stock market direction Panchal Amitkumar Mansukhbhai 1, Dr. Jayeshkumar Madhubhai Patel 2 1. Ph.D Research Scholar, Gujarat Technological University,

More information

Prediction of Stock Closing Price by Hybrid Deep Neural Network

Prediction of Stock Closing Price by Hybrid Deep Neural Network Available online www.ejaet.com European Journal of Advances in Engineering and Technology, 2018, 5(4): 282-287 Research Article ISSN: 2394-658X Prediction of Stock Closing Price by Hybrid Deep Neural Network

More information

Forecast Horizons for Production Planning with Stochastic Demand

Forecast Horizons for Production Planning with Stochastic Demand Forecast Horizons for Production Planning with Stochastic Demand Alfredo Garcia and Robert L. Smith Department of Industrial and Operations Engineering Universityof Michigan, Ann Arbor MI 48109 December

More information

INDIAN INSTITUTE OF SCIENCE STOCHASTIC HYDROLOGY. Lecture -26 Course Instructor : Prof. P. P. MUJUMDAR Department of Civil Engg., IISc.

INDIAN INSTITUTE OF SCIENCE STOCHASTIC HYDROLOGY. Lecture -26 Course Instructor : Prof. P. P. MUJUMDAR Department of Civil Engg., IISc. INDIAN INSTITUTE OF SCIENCE STOCHASTIC HYDROLOGY Lecture -26 Course Instructor : Prof. P. P. MUJUMDAR Department of Civil Engg., IISc. Summary of the previous lecture Hydrologic data series for frequency

More information

Université de Montréal. Rapport de recherche. Empirical Analysis of Jumps Contribution to Volatility Forecasting Using High Frequency Data

Université de Montréal. Rapport de recherche. Empirical Analysis of Jumps Contribution to Volatility Forecasting Using High Frequency Data Université de Montréal Rapport de recherche Empirical Analysis of Jumps Contribution to Volatility Forecasting Using High Frequency Data Rédigé par : Imhof, Adolfo Dirigé par : Kalnina, Ilze Département

More information