Data driven value-at-risk forecasting using a SVR-GARCH-KDE hybrid

Appropriate risk management is crucial to ensure the competitiveness of financial institutions and the stability of the economy. One widely used financial risk measure is Value-at-Risk (VaR). VaR estimates based on linear and parametric models can lead to biased results or even underestimation of risk due to time varying volatility, skewness and leptokurtosis of financial return series. The paper proposes a nonlinear and nonparametric framework to forecast VaR that is motivated by overcoming the disadvantages of parametric models with a purely data driven approach. Mean and volatility are modeled via support vector regression (SVR) where the volatility model is motivated by the standard generalized autoregressive conditional heteroscedasticity (GARCH) formulation. Based on this, VaR is derived by applying kernel density estimation (KDE). This approach allows for flexible tail shapes of the profit and loss distribution, adapts for a wide class of tail events and is able to capture complex structures regarding mean and volatility. The SVR-GARCH-KDE hybrid is compared to standard, exponential and threshold GARCH models coupled with different error distributions. To examine the performance in different markets, one-day-ahead and ten-days-ahead forecasts are produced for different financial indices. Model evaluation using a likelihood ratio based test framework for interval forecasts and a test for superior predictive ability indicates that the SVR-GARCH-KDE hybrid performs competitive to benchmark models and reduces potential losses especially for ten-days-ahead forecasts significantly. Especially models that are coupled with a normal distribution are systematically outperformed.

[1]  Pei-Chann Chang,et al.  A Takagi-Sugeno fuzzy model combined with a support vector regression for stock trading forecasting , 2016, Appl. Soft Comput..

[2]  Ashraful Islam Khan,et al.  Modelling daily value-at-risk using realized volatility, non-linear support vector machine and ARCH type models , 2011 .

[3]  P. Hansen.  A Test for Superior Predictive Ability , 2005 .

[4]  Franke Jürgen,et al.  Estimating market risk with neural networks , 2006 .

[5]  Robert A. Lordo,et al.  Nonparametric and Semiparametric Models , 2005, Technometrics.

[6]  Wolfgang Härdle,et al.  GitHub API based QuantNet Mining infrastructure in R , 2017 .

[7]  Liang Peng,et al.  Interval estimation of value-at-risk based on GARCH models with heavy-tailed innovations , 2007 .

[8]  Julia Schaumburg,et al.  Predicting extreme value at risk: Nonparametric quantile regression with refinements from extreme value theory , 2012, Comput. Stat. Data Anal..

[9]  Wolfgang Härdle,et al.  Handbook of Big Data Analytics , 2018 .

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

[11]  D. Ruppert.  The Elements of Statistical Learning: Data Mining, Inference, and Prediction , 2004 .

[12]  Huei-Mei Liang,et al.  Estimating value at risk of portfolio by conditional copula-GARCH method , 2009 .

[13]  Saeid Nahavandi,et al.  A neural network-GARCH-based method for construction of Prediction Intervals , 2013 .

[14]  Vladimir Vapnik,et al.  The Nature of Statistical Learning , 1995 .

[15]  Kiho Jeong,et al.  Forecasting volatility with support vector machine-based GARCH model , 2009 .

[16]  Jose A. Lopez,et al.  Methods for Evaluating Value-at-Risk Estimates , 1998 .

[17]  Chih-Jen Lin,et al.  Asymptotic Behaviors of Support Vector Machines with Gaussian Kernel , 2003, Neural Computation.

[18]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[19]  P. J. Green,et al.  Density Estimation for Statistics and Data Analysis , 1987 .

[20]  F. Tay,et al.  Application of support vector machines in financial time series forecasting , 2001 .

[21]  Bernhard Schölkopf,et al.  A tutorial on support vector regression , 2004, Stat. Comput..

[22]  Georgios Sermpinis,et al.  Modelling commodity value at risk with higher order neural networks , 2010 .

[23]  Herbert Kimura,et al.  An analysis of the literature on systemic financial risk: A survey , 2017 .

[24]  W. Härdle,et al.  Downside riskand stock returns , 2016 .

[25]  Yi-Ming Wei,et al.  Estimating ‘Value at Risk’ of crude oil price and its spillover effect using the GED-GARCH approach , 2008 .

[26]  W. Härdle,et al.  Statistics of Financial Markets: An Introduction , 2004 .

[27]  Sergey Sarykalin,et al.  Value-at-Risk vs. Conditional Value-at-Risk in Risk Management and Optimization , 2008 .

[28]  Campbell R. Harvey,et al.  Conditional Skewness in Asset Pricing Tests , 1999 .

[29]  Turan G. Bali,et al.  The role of autoregressive conditional skewness and kurtosis in the estimation of conditional VaR , 2008 .

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

[31]  Qian Chen,et al.  Computational Statistics and Data Analysis Bayesian Value-at-risk and Expected Shortfall Forecasting via the Asymmetric Laplace Distribution , 2022 .

[32]  Claudia Czado,et al.  D-vine copula based quantile regression , 2015, Comput. Stat. Data Anal..

[33]  Manel Youssef,et al.  Value-at-Risk estimation of energy commodities: A long-memory GARCH–EVT approach , 2015 .

[34]  Peter F. CHRISTOFFERSENti.  EVALUATING INTERVAL FORECASTS , 2016 .

[35]  Farookh Khadeer Hussain,et al.  Support vector regression with chaos-based firefly algorithm for stock market price forecasting , 2013, Appl. Soft Comput..

[36]  G. Prem Kumar,et al.  Cuckoo optimized SVM for stock market prediction , 2015, 2015 International Conference on Innovations in Information, Embedded and Communication Systems (ICIIECS).

[37]  Hossam Faris,et al.  A Comparison between Regression, Artificial Neural Networks and Support Vector Machines for Predicting Stock Market Index , 2015 .

[38]  Wu Meng,et al.  Application of Support Vector Machines in Financial Time Series Forecasting , 2007 .

[39]  Hsuan-Tien Lin.  A Study on Sigmoid Kernels for SVM and the Training of non-PSD Kernels by SMO-type Methods , 2005 .

[40]  Stefan Lessmann,et al.  Car resale price forecasting: The impact of regression method, private information, and heterogeneity on forecast accuracy , 2017 .

[41]  O. Radović,et al.  Tail Risk Assessment Using Support Vector Machine , 2015 .

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

[43]  Chaker Aloui,et al.  Value-at-risk estimations of energy commodities via long-memory, asymmetry and fat-tailed GARCH models , 2010 .

[44]  Peter Malec,et al.  Nonparametric Kernel Density Estimation Near the Boundary , 2013, Comput. Stat. Data Anal..

[45]  Marc S. Paolella,et al.  Accurate value-at-risk forecasting based on the normal-GARCH model , 2006, Comput. Stat. Data Anal..

[46]  J. Zakoian.  Threshold heteroskedastic models , 1994 .

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

[48]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[49]  Sangyeol Lee,et al.  Nonlinear expectile regression with application to Value-at-Risk and expected shortfall estimation , 2016, Comput. Stat. Data Anal..

[50]  Qifa Xu,et al.  An exponentially weighted quantile regression via SVM with application to estimating multiperiod VaR , 2015, Statistical Methods & Applications.

[51]  Peter Christoffersen,et al.  Value–at–Risk Models , 2009 .