The best of two worlds: Forecasting high frequency volatility for cryptocurrencies and traditional currencies with Support Vector Regression

Abstract This paper provides an evaluation of the predictive performance of the volatility of three cryptocurrencies and three currencies with recognized stores of value using daily and hourly frequency data. We combined the traditional GARCH model with the machine learning approach to volatility estimation, estimating the mean and volatility equations using Support Vector Regression (SVR) and comparing to GARCH family models. Furthermore, the models’ predictive ability was evaluated using Diebold-Mariano test and Hansen’s Model Confidence Set. The analysis was reiterated for both low and high frequency data. Results showed that SVR-GARCH models managed to outperform GARCH, EGARCH and GJR-GARCH models with Normal, Student’s t and Skewed Student’s t distributions. For all variables and both time frequencies, the SVR-GARCH model exhibited statistical significance towards its superiority over GARCH and its extensions.

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

[2]  David Chaum,et al.  Blind Signatures for Untraceable Payments , 1982, CRYPTO.

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

[4]  Sibel Celik,et al.  Volatility forecasting using high frequency data: Evidence from stock markets , 2014 .

[5]  Daniel B. Nelson,et al.  Filtering and Forecasting with Misspecified Arch Models Ii: Making the Right Forecast with the Wrong Model , 1992 .

[6]  Guido Deboeck,et al.  Trading on the Edge: Neural, Genetic, and Fuzzy Systems for Chaotic Financial Markets , 1994 .

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

[8]  J. Matías,et al.  Nonlinearity in Forecasting of High-Frequency Stock Returns , 2012 .

[9]  Ansgar Belke,et al.  Contagion, herding and exchange-rate instability — A survey , 2004 .

[10]  R. Cont.  Empirical properties of asset returns: stylized facts and statistical issues , 2001 .

[11]  Jozef Baruník,et al.  Combining high frequency data with non-linear models for forecasting energy market volatility , 2016, Expert Syst. Appl..

[12]  Kevin Dowd,et al.  New Private Monies: A Bit-Part Player? , 2014 .

[13]  A. H. Dyhrberg.  Hedging capabilities of bitcoin. Is it the virtual gold , 2016 .

[14]  A. H. Dyhrberg.  Bitcoin, gold and the dollar – A GARCH volatility analysis , 2016 .

[15]  Shen Furao,et al.  Forecasting exchange rate using deep belief networks and conjugate gradient method , 2015, Neurocomputing.

[16]  Amir F. Atiya,et al.  Introduction to financial forecasting , 1996, Applied Intelligence.

[17]  C. Granger,et al.  A long memory property of stock market returns and a new model , 1993 .

[18]  Geoffrey Lightfoot,et al.  Price Fluctuations and the Use of Bitcoin: An Empirical Inquiry , 2015, Int. J. Electron. Commer..

[19]  L. Glosten,et al.  On the Relation between the Expected Value and the Volatility of the Nominal Excess Return on Stocks , 1993 .

[20]  Peter Reinhard Hansen,et al.  The Model Confidence Set , 2010 .

[21]  LiXin,et al.  The technology and economic determinants of cryptocurrency exchange rates: The case of Bitcoin , 2017, Decis. Support Syst..

[22]  Georgios Sermpinis,et al.  Modeling, forecasting and trading the EUR exchange rates with hybrid rolling genetic algorithms - Support vector regression forecast combinations , 2015, Eur. J. Oper. Res..

[23]  J. Frausto-Solis,et al.  Volatility Forecasting Using Support Vector Regression and a Hybrid Genetic Algorithm , 2013, Computational Economics.

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

[25]  Valeriy V. Gavrishchaka,et al.  Support Vector Machine as an Efficient Framework for Stock Market Volatility Forecasting , 2006, Comput. Manag. Sci..

[26]  Zhongyi Hu,et al.  Multiple-output support vector regression with a firefly algorithm for interval-valued stock price index forecasting , 2014, Knowl. Based Syst..

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

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

[29]  Chen Zhou,et al.  Diagnosing the distribution of GARCH innovations , 2014 .

[30]  Chih-Jen Lin,et al.  Training v-Support Vector Regression: Theory and Algorithms , 2002, Neural Computation.

[31]  S. Laurent,et al.  On the Forecasting Accuracy of Multivariate GARCH Models , 2010 .

[32]  Andrew Urquhart.  The Inefficiency of Bitcoin , 2016 .

[33]  Neil Gandal,et al.  Competition in the Cryptocurrency Market , 2014, SSRN Electronic Journal.

[34]  Elie Bouri,et al.  On the return-volatility relationship in the Bitcoin market around the price crash of 2013 , 2016 .

[35]  Alexander J. Smola,et al.  Support Vector Regression Machines , 1996, NIPS.

[36]  Xin Li,et al.  The Technology and Economic Determinants of Cryptocurrency Exchange Rates: The Case of Bitcoin , 2014, Decis. Support Syst..

[37]  T. Bollerslev,et al.  Deutsche Mark–Dollar Volatility: Intraday Activity Patterns, Macroeconomic Announcements, and Longer Run Dependencies , 1998 .

[38]  N. Ferguson.  The Ascent of Money: A Financial History of the World , 2008 .

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

[40]  Juri Marcucci.  Forecasting Stock Market Volatility with Regime-Switching GARCH Models , 2005 .

[41]  Ma Li,et al.  Forex Prediction Based on SVR Optimized by Artificial Fish Swarm Algorithm , 2013, 2013 Fourth Global Congress on Intelligent Systems.

[42]  Pedro Correia S. Bezerra,et al.  Volatility forecasting via SVR–GARCH with mixture of Gaussian kernels , 2017, Comput. Manag. Sci..

[43]  W. Härdle,et al.  Support Vector Regression Based GARCH Model with Application to Forecasting Volatility of Financial Returns , 2008 .

[44]  Marcin Andrychowicz,et al.  Fair Two-Party Computations via Bitcoin Deposits , 2014, Financial Cryptography Workshops.

[45]  Ladislav Kristoufek,et al.  What Are the Main Drivers of the Bitcoin Price? Evidence from Wavelet Coherence Analysis , 2014, PloS one.

[46]  A. Tiwari,et al.  Does Bitcoin hedge global uncertainty? Evidence from wavelet-based quantile-in-quantile regressions , 2016 .

[47]  Dean P. Foster,et al.  Filtering and Forecasting with Misspecified Arch Models Ii: Making the Right Forecast with the Wrong Model , 1992 .

[48]  Yi-Hsien Wang,et al.  Nonlinear neural network forecasting model for stock index option price: Hybrid GJR-GARCH approach , 2009, Expert Syst. Appl..

[49]  Jian Li,et al.  Intraday Volatility Analysis on S&P 500 Stock Index Future , 2010 .

[50]  Fatos Xhafa,et al.  Utilizing artificial neural networks and genetic algorithms to build an algo-trading model for intra-day foreign exchange speculation , 2013, Math. Comput. Model..

[51]  A. McNeil,et al.  Estimation of tail-related risk measures for heteroscedastic financial time series: an extreme value approach , 2000 .

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

[53]  David S. Evans,et al.  Economic Aspects of Bitcoin and Other Decentralized Public-Ledger Currency Platforms , 2014 .

[54]  Stefan Lessmann,et al.  Bridging the divide in financial market forecasting: machine learners vs. financial economists , 2016, Expert Syst. Appl..

[55]  C. Granger,et al.  Forecasting Volatility in Financial Markets: A Review , 2003 .

[56]  Meni Rosenfeld,et al.  Analysis of Hashrate-Based Double Spending , 2014, ArXiv.

[57]  Leandro dos Santos Coelho,et al.  Computational intelligence approaches and linear models in case studies of forecasting exchange rates , 2007, Expert Syst. Appl..

[58]  M. Elbeck,et al.  Bitcoins as an investment or speculative vehicle? A first look , 2015 .

[59]  D. Yermack.  Is Bitcoin a Real Currency? An Economic Appraisal , 2013 .

[60]  R. C. Merton,et al.  On Estimating the Expected Return on the Market: An Exploratory Investigation , 1980 .

[61]  Valentina Corradi,et al.  Predicting the volatility of the S&P-500 stock index via GARCH models: the role of asymmetries , 2005 .

[62]  The Volume Clock: Insights into the High-Frequency Paradigm , 2012, The Journal of Portfolio Management.

[63]  Darlington,et al.  The Future of Bitcoin: Mapping the Global Adoption of World’s Largest Cryptocurrency Through Benefit Analysis , 2014 .

[64]  Francis Eng Hock Tay,et al.  Support vector machine with adaptive parameters in financial time series forecasting , 2003, IEEE Trans. Neural Networks.

[65]  Christofer Toumazou,et al.  Improving prediction of exchange rates using Differential EMD , 2013, Expert Syst. Appl..

[66]  Valeriy V. Gavrishchaka,et al.  Volatility forecasting from multiscale and high-dimensional market data , 2003, Neurocomputing.

[67]  Tai-Hoon Kim.  A Study of Digital Currency Cryptography for Bbusiness Marketing and Finance Security , 2016 .

[68]  LessmannStefan,et al.  Bridging the divide in financial market forecasting , 2016 .