Boosting the Anatomy of Volatility

Risk and, thus, the volatility of financial asset prices plays a major role in financial decision making and financial regulation. Therefore, understanding and predicting the volatility of financial instruments, asset classes or financial markets in general is of utmost importance for individual and institutional investors as well as for central bankers and financial regulators. In this paper we investigate new strategies for understanding and predicting financial risk. Specifically, we use componentwise, gradient boosting techniques to identify factors that drive financial-market risk and to assess the specific nature with which these factors affect future volatility. Componentwise boosting is a sequential learning method, which has the advantages that it can handle a large number of predictors and that it-in contrast to other machine-learning techniques-preserves interpretation. Adopting an EGARCH framework and employing a wide range of potential risk drivers, we derive monthly volatility predictions for stock, bond, commodity, and foreign exchange markets. Comparisons with alternative benchmark models show that boosting techniques improve out-of-sample volatility forecasts, especially for medium- and long-run horizons. Another finding is that a number of risk drivers affect volatility in a nonlinear fashion.

[1]  R. Engle.  Autoregressive conditional heteroscedasticity with estimates of the variance of United Kingdom inflation , 1982 .

[2]  Charlotte Christiansen,et al.  A Comprehensive Look at Financial Volatility Prediction by Economic Variables , 2011 .

[3]  K. French,et al.  Expected stock returns and volatility , 1987 .

[4]  K. Hornik,et al.  Unbiased Recursive Partitioning: A Conditional Inference Framework , 2006 .

[5]  B. Yu,et al.  Boosting with the L 2-loss regression and classification , 2001 .

[6]  P. Hansen,et al.  A Forecast Comparison of Volatility Models: Does Anything Beat a Garch(1,1)? , 2004 .

[7]  J. Cochrane,et al.  Bond Risk Premia , 2002 .

[8]  P. Bühlmann,et al.  Volatility estimation with functional gradient descent for very high-dimensional financial time series , 2003 .

[9]  Gerhard Tutz,et al.  Boosting techniques for nonlinear time series models , 2012 .

[10]  Peter L. Bartlett,et al.  Functional Gradient Techniques for Combining Hypotheses , 2000 .

[11]  Andrew J. Patton.  Volatility Forecast Comparison Using Imperfect Volatility Proxies , 2006 .

[12]  Paras Gupta,et al.  Common Risk Factors in Currency Markets , 2012 .

[13]  Yoav Freund,et al.  Experiments with a New Boosting Algorithm , 1996, ICML.

[14]  Leo Breiman,et al.  Classification and Regression Trees , 1984 .

[15]  Hans C. van Houwelingen,et al.  The Elements of Statistical Learning, Data Mining, Inference, and Prediction. Trevor Hastie, Robert Tibshirani and Jerome Friedman, Springer, New York, 2001. No. of pages: xvi+533. ISBN 0‐387‐95284‐5 , 2004 .

[16]  Leslie G. Valiant,et al.  Cryptographic Limitations on Learning Boolean Formulae and Finite Automata , 1993, Machine Learning: From Theory to Applications.

[17]  F. Diebold,et al.  Comparing Predictive Accuracy , 1994, Business Cycles.

[18]  Peter Buhlmann,et al.  BOOSTING ALGORITHMS: REGULARIZATION, PREDICTION AND MODEL FITTING , 2007, 0804.2752.

[19]  P. Hansen,et al.  A Forecast Comparison of Volatility Models: Does Anything Beat a Garch(1,1)? , 2004 .

[20]  Georgeann Portokalis,et al.  Carry Trades and Global Foreign Exchange Volatility , 2012 .

[21]  G. Schwert.  Why Does Stock Market Volatility Change Over Time? , 1988 .

[22]  P. Bühlmann,et al.  Splines for financial volatility , 2007 .

[23]  S. B. Thompson,et al.  Predicting Excess Stock Returns Out of Sample: Can Anything Beat the Historical Average? , 2008 .

[24]  P. Bühlmann,et al.  Boosting with the L2-loss: regression and classification , 2001 .

[25]  Paul Newbold,et al.  Testing the equality of prediction mean squared errors , 1997 .

[26]  F. Diebold,et al.  VOLATILITY AND CORRELATION FORECASTING , 2006 .

[27]  Bradley S. Paye,et al.  Deja Vol: Predictive Regressions for Aggregate Stock Market Volatility Using Macroeconomic Variables , 2011 .

[28]  Serena Ng,et al.  Boosting diffusion indices , 2009 .

[29]  I. Welch,et al.  A Comprehensive Look at the Empirical Performance of Equity Premium Prediction II , 2004, SSRN Electronic Journal.

[30]  T. Bollerslev,et al.  Generalized autoregressive conditional heteroskedasticity , 1986 .

[31]  Benjamin Hofner,et al.  Generalized additive models for location, scale and shape for high dimensional data—a flexible approach based on boosting , 2012 .

[32]  Trevor Hastie,et al.  The Elements of Statistical Learning , 2001 .

[33]  Leo Breiman,et al.  Prediction Games and Arcing Algorithms , 1999, Neural Computation.

[34]  Robert Tibshirani,et al.  The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd Edition , 2001, Springer Series in Statistics.

[35]  Francis X. Diebold,et al.  Modeling and Forecasting Realized Volatility , 2001 .

[36]  R. Engle,et al.  On the Economic Sources of Stock Market Volatility , 2008 .

[37]  Luis M. Viceira,et al.  Bond Risk, Bond Return Volatility, and the Term Structure of Interest Rates , 2007 .

[38]  S. Mittnik,et al.  The Volatility of Realized Volatility , 2005 .

[39]  Leo Breiman,et al.  Bagging Predictors , 1996, Machine Learning.

[40]  José M. Matías,et al.  Boosting GARCH and neural networks for the prediction of heteroskedastic time series , 2010, Math. Comput. Model..

[41]  L. Breiman.  Arcing Classifiers , 1998 .

[42]  Daniel B. Nelson.  CONDITIONAL HETEROSKEDASTICITY IN ASSET RETURNS: A NEW APPROACH , 1991 .

[43]  Philippe Jorion.  Predicting Volatility in the Foreign Exchange Market , 1995 .

[44]  Yoav Freund,et al.  Boosting the margin: A new explanation for the effectiveness of voting methods , 1997, ICML.

[45]  Peter Bühlmann,et al.  An algorithm for nonparametric GARCH modelling , 2002 .

[46]  J. Friedman.  Greedy function approximation: A gradient boosting machine. , 2001 .

[47]  Roberto Cardarelli,et al.  Financial Stress, Downturns, and Recoveries , 2009, SSRN Electronic Journal.

[48]  Stefan Mittnik,et al.  Forecasting stock market volatility and the informational efficiency of the DAX-index options market , 2002 .

[49]  R Core Team,et al.  R: A language and environment for statistical computing. , 2014 .

[50]  Marc S. Paolella,et al.  Value-at-Risk Prediction: A Comparison of Alternative Strategies , 2005 .

[51]  R. Rigby,et al.  Generalized additive models for location, scale and shape , 2005 .

[52]  Y. Freund,et al.  Discussion of the Paper \additive Logistic Regression: a Statistical View of Boosting" By , 2000 .

[53]  Helmut Strasser,et al.  On the Asymptotic Theory of Permutation Statistics , 1999 .