Robustness of Support Vector Machines in Algorithmic Trading on Cryptocurrency Market

Ślepaczuk, Robert; Zenkova, Maryna

doi:10.1515/ceej-2018-0022

Abstract

This study investigates the profitability of an algorithmic trading strategy based on training SVM model to identify cryptocurrencies with high or low predicted returns. A tail set is defined to be a group of coins whose volatility-adjusted returns are in the highest or the lowest quintile. Each cryptocurrency is represented by a set of six technical features. SVM is trained on historical tail sets and tested on the current data. The classifier is chosen to be a nonlinear support vector machine. The portfolio is formed by ranking coins using the SVM output. The highest ranked coins are used for long positions to be included in the portfolio for one reallocation period. The following metrics were used to estimate the portfolio profitability: %ARC (the annualized rate of change), %ASD (the annualized standard deviation of daily returns), MDD (the maximum drawdown coefficient), IR1, IR2 (the information ratio coefficients). The performance of the SVM portfolio is compared to the performance of the four benchmark strategies based on the values of the information ratio coefficient IR1, which quantifies the risk-weighted gain. The question of how sensitive the portfolio performance is to the parameters set in the SVM model is also addressed in this study.

References

Boyd, S., Vandenberghe, L., 2004. ‘Convex Optimization’ Cambridge University Press New York, NY, USA.
Search in Google Scholar Back to article
Cawley, G., Talbot, N., 2010. ‘On over-fitting in model selection and subsequent selection bias in performance evaluation’ J. Mach. Learn. Res. 11, 2079–2107.
Search in Google Scholar Back to article
Chen M., Narwal N., Schultz. M., 2018, Stanford University. Predicting Price Changes in Ethereum. URL: https://pdfs.semanticscholar.org/ceff/65e02b2b9b6b181cfc956350351b8e284a01.pdf?_ga=2.139748214.472574922.1533418619-1566045322.1533418619
Search in Google Scholar Back to article
Chordia, T., Swaminathan, B., 2002. ‘Trading volume and cross-autocorrelations in stock returns’ J. Financ. 55 (2), 913–935.
Search in Google Scholar Back to article
Cristianini, N. and Shawe-Taylor, J. 2000, ‘An Introduction to Support Vector Machines and Other Kernel-Based Learning Methods’ Cambridge University Press Cambridge.
Search in Google Scholar Back to article
David Meyer. Support Vector Machines. The Interface to libsvm in package e1071. URL: https://cran.r-project.org/web/packages/e1071/vignettes/svmdoc.pdf
Search in Google Scholar Back to article
Hastie, T., Tibshirani, R., Friedman, J., ‘The Elements of Statistical Learning’ Data Mining, Inference, and Prediction.
Search in Google Scholar Back to article
Huang, W., Nakamori, Y., Wang, S.-Y., 2005. ‘Forecasting stock market movement direction with support vector machine’ Comput. Oper. Res 32 (10), 2513–2522.
Search in Google Scholar Back to article
Huang, Z., Chen, H., Hsu, C.J., Chen, W.H., Wu, S., 2004. ‘Credit rating analysis with support vector machines and neural networks: A market comparative study’ Decis. Support Syst. 37 (4), 543–558.
Search in Google Scholar Back to article
Huerta, R., Corbacho, F., Elkan, C., 2013. ‘Nonlinear support vector machines can systematically identify stocks with high and low future returns’ IOS Press. Algorithmic Finance 2, (45–58).
Search in Google Scholar Back to article
Huffman, S., Moll, C., 2011. ‘The impact of asymmetry on expected stock returns: An investigation of alternative risk measures’ Algorithmic Financ 1 (2), 79–93.
Search in Google Scholar Back to article
James, G., Witten, D., Hastie, T., Tibshirani, R., ‘An Introduction to Statistical Learning with Applications in R’.
Search in Google Scholar Back to article
Jegadeesh, N., Titman, S., 2012. ‘Returns to buying winners and selling losers: Implications for stock market efficiency’ J Financ. 48 (1), 65–91.
Search in Google Scholar Back to article
Joachims, T. 1998. ‘Text categorization with Support Vector Machines: Learning with many relevant features. European Conference on Machine Learning ECML’ 1998: Machine Learning: ECML-98 pp 137–142.
Search in Google Scholar Back to article
Kim, K., 2003. ‘Financial time series forecasting using support vector machines. Neurocomputing’ 55 (1), 307–319.
Search in Google Scholar Back to article
Kość K., Sakowski P., Ślepaczuk R., 2018,Momentum and Contrarian Effects on the Cryptocurrency Market Physica A 523, 691–701, https://www.sciencedirect.com/science/article/pii/S037843711930216X?dgcid=author
Search in Google Scholar Back to article
Meyer D., Misc Functions of the Department of Statistics, Probability Theory Group (Formerly: E1071), TU Wien. Package ‘e1071’. URL: https://cran.r-project.org/web/packages/e1071/e1071.pdf
Search in Google Scholar Back to article
Muller, K., Mika, S., Ratsch, G., Tsuda, K., Scholkopf, B., 2001. ‘An introduction to kernel-based learning algorithms’ IEEE Neural Network 12 (2), 181–201.
Search in Google Scholar Back to article
Package “TTR”. URL: https://cran.r-project.org/web/packages/TTR/TTR.pdf
Search in Google Scholar Back to article
Performance Analytics in R. URL: https://cran.r-project.org/web/packages/PerformanceAnalytics/vignettes/portfolio_returns.pdf
Search in Google Scholar Back to article
Pistole, T.C. ‘Comparison of three technical trading methods vs. buy-and-hold for the S&P 500 market. Graduate Student of Finance’, University of Houston – Victoria. URL: http://swdsi.org/swdsi2010/SW2010_Preceedings/papers/PA153.pdf
Search in Google Scholar Back to article
Rouwenhorst, K., 2002. ‘International momentum strategies’ J. Financ. 53 (1), 267–284.
Search in Google Scholar Back to article
Sewell, M., 2010. ‘The Application of Intelligent Systems to Financial Time Series Analysis, PhD thesis, PhD dissertation, Department of Computer Science’, University College London University of London.
Search in Google Scholar Back to article
Ślepaczuk R., Sakowski P., Zakrzewski G., 2018, Investment strategies beating the market. What can we squeeze from the market? eFinanse Vol. 14, no. 4, s. 36-55, https://e-finanse.com/current-issue/?number=59&id=421
Search in Google Scholar Back to article
Tay, F., Cao, L., 2001. ‘Application of support vector machines in financial time series forecasting’ Omega 29 (4), 309–317.
Search in Google Scholar Back to article
Tay, F., Cao, L., 2002. ‘Modified support vector machines in financial time series forecasting’ Neurocomputing 48 (1), 847–861.
Search in Google Scholar Back to article
Van Gestel, T., Suykens, J., Baestaens, D., Lambrechts, A., Lanckriet, G., Vandaele, B., et. hal., 2001. ‘Financial time series prediction using least squares support vector machines within the evidence framework’ Neural Netw., IEEE Trans 12 (4), 809–821.
Search in Google Scholar Back to article
Vapnik, V., 1999. ‘The Nature of Statistical Learning Theory’ Springer, Heidelberg, Germany.
Search in Google Scholar Back to article

Robustness of Support Vector Machines in Algorithmic Trading on Cryptocurrency Market

Abstract

Paradigm

My account