Abstract
Machine learning and artificial intelligence techniques have been applied to construct online portfolio selection strategies recently. A popular and state-of-the-art family of strategies is to explore the reversion phenomenon through online learning algorithms and statistical prediction models. Despite gaining promising results on some benchmark datasets, these strategies often adopt a single model based on a selection criterion (e.g., breakdown point) for predicting future price. However, such model selection is often unstable and may cause unnecessarily high variability in the final estimation, leading to poor prediction performance in real datasets and thus non-optimal portfolios. To overcome the drawbacks, in this article, we propose to exploit the reversion phenomenon by using combination forecasting estimators and design a novel online portfolio selection strategy, named Combination Forecasting Reversion (CFR), which outputs optimal portfolios based on the improved reversion estimator. We further present two efficient CFR implementations based on online Newton step (ONS) and online gradient descent (OGD) algorithms, respectively, and theoretically analyze their regret bounds, which guarantee that the online CFR model performs as well as the best CFR model in hindsight. We evaluate the proposed algorithms on various real markets with extensive experiments. Empirical results show that CFR can effectively overcome the drawbacks of existing reversion strategies and achieve the state-of-the-art performance.
Supplemental Material
Available for Download
Supplemental movie, appendix, image and software files for, Combination Forecasting Reversion Strategy for Online Portfolio Selection
- Amit Agarwal, Elad Hazan, Satyen Kale, and Robert E. Schapire. 2006. Algorithms for portfolio management based on the Newton method. In Proceedings of the International Conference on Machine Learning. 9--16. Google ScholarDigital Library
- Oren Anava, Elad Hazan, Shie Mannor, and Ohad Shamir. 2013. Online learning for time series prediction. J. Mach. Learn. Res. 30, 172--184.Google Scholar
- J. Scott Armstrong. 2001. Combining forecasts. In Principles of Forecasting. International Series in Operations Research and Management Science, Vol. 30. Springer. 417--439.Google Scholar
- N. Balamurali and S. Sivarajasingam. 2011. Dynamic relationship between stock prices and exchange rates: Evidence from Sri Lanka. Int. J. Theor. Appl. Finan. 9, 8, 1377.Google Scholar
- J. M. Bates and C. W. J. Granger. 1969. The combination of forecasts. J. Operat. Res. Soc. 20, 4, 451--468.Google ScholarCross Ref
- Avrim Blum and Adam Kalai. 1999. Universal portfolios with and without transaction costs. Mach. Learn. 35, 3, 193--205. Google ScholarDigital Library
- A. Borodin, R. El-Yaniv, and V. Gogan. 2011. Can we learn to beat the best stock? J. Artific. Intell. Res. 21, 579--594. Google ScholarDigital Library
- S. Boyd and L. Vandenberghe. 2004. Convex Optimization. Cambridge University Press, Cambridge, UK. Google ScholarDigital Library
- Leo Breiman. 1996. Bagging predictors. Mach. Learn. 24, 2, 123--140. Google ScholarDigital Library
- Leo Breiman. 1996. Stacked regressions. Mach. Learn. 24, 1, 49--64. Google ScholarDigital Library
- Nicolo Cesa-Bianchi and Gabor Lugosi. 2006. Prediction, Learning, and Games. Cambridge University Press, Cambridge, UK. Google Scholar
- R. Chandrasekaran and A. Tamir. 1989. Open questions concerning Weiszfeld’s algorithm for the Fermat-Weber location problem. Math. Program. 44, 1, 293--295.Google ScholarCross Ref
- Gerda Claeskens, Jan R. Magnus, Andrey L. Vasnev, and Wendun Wang. 2016. The forecast combination puzzle: A simple theoretical explanation. Int. J. Forecast. 32, 3, 754--762.Google ScholarCross Ref
- Thomas M. Cover. 1991. Universal portfolios. Math. Finance 1, 1, 1--29.Google ScholarCross Ref
- Thomas M. Cover and Erik Ordentlich. 1996. Universal portfolios with side information. IEEE Trans. Info. Theory 42, 2, 348--363. Google ScholarDigital Library
- Thomas M. Cover and Joy A. Thomas. 1991. Elements of Information Theory. Wiley, New York, NY. Google ScholarDigital Library
- Koby Crammer, Ofer Dekel, Joseph Keshet, Shai Shalev-Shwartz, and Yoram Singer. 2006. Online passive-aggressive algorithms. J. Mach. Learn. Res. 7, 3, 551--585. Google ScholarDigital Library
- Thomas G. Dietterich. 2000. Ensemble methods in machine learning. In Multiple Classifier Systems. Lecture Notes in Computer Science, Vol. 1857. Springer, 1--15. Google ScholarDigital Library
- Harris Drucker. 1997. Improving regressors using boosting techniques. In Proceedings of the 14th International Conference on Machine Learning. 107--115. Google ScholarDigital Library
- John Duchi, Shai ShalevShwartz, Yoram Singer, and Tushar Chandra. 2008. Efficient projections onto the -ball for learning in high dimensions. In Proceedings of the International Conference on Machine Learning. 272--279. Google ScholarDigital Library
- Nigel Duffy and David Helmbold. 2002. Boosting methods for regression. Mach. Learn. 47, 2--3, 153--200. Google ScholarDigital Library
- Alexei A. Gaivoronski and Fabio Stella. 2000. Stochastic nonstationary optimization for finding universal portfolios. Ann. Operat. Res. 100, 1--4, 165--188.Google ScholarCross Ref
- Richard Grinold and Ronald Kahn. 1999. Active Portfolio Management: A Quantitative Approach for Producing Superior Returns and Controlling Risk. McGraw-Hill, New York, NY.Google Scholar
- László Györfi, Gábor Lugosi, and Frederic Udina. 2006. Nonparametric kernel-based sequential investment strategies. Math. Finance 16, 2, 337--357.Google ScholarCross Ref
- László Györfi, Frederic Udina, and Harro Walk. 2008. Nonparametric nearest neighbor based empirical portfolio selection strategies. Int. Math. J. Stochast. Methods Models 26, 2, 145--157.Google Scholar
- Elad Hazan, Amit Agarwal, and Satyen Kale. 2007. Logarithmic regret algorithms for online convex optimization. Mach. Learn. 69, 2--3, 169--192. Google ScholarDigital Library
- Elad Hazan, Adam Tauman Kalai, Satyen Kale, and Amit Agarwal. 2006. Logarithmic regret algorithms for online convex optimization. In Proceedings of the Annual Conference on Learning Theory, Vol. 4005. 499--513. Google ScholarDigital Library
- David P. Helmbold, Robert E. Schapire, Yoram Singer, and Manfred K. Warmuth. 1996. On-line portfolio selection using multiplicative updates. In Proceedings of the 13th International Conference on Machine Learning. 243--251. Google ScholarDigital Library
- Dingjiang Huang, Junlong Zhou, Bin Li, Steven C. H. Hoi, and Shuigeng Zhou. 2013. Robust median reversion strategy for on-line portfolio selection. In Proceedings of the International Joint Conference on Artificial Intelligence. 2006--2012. Google ScholarDigital Library
- Rob J. Hyndman, Roman A. Ahmed, George Athanasopoulos, and Han Lin Shang. 2011. Optimal combination forecasts for hierarchical time series. Comput. Stat. Data Anal. 55, 9, 2579--2589. Google ScholarDigital Library
- J. L. Kelly Jr. 1956. A new interpretation of information rate. AT8T Tech. J. 35, 917--926.Google Scholar
- Fusun Kucukbay and Ceyhun Araz. 2016. Portfolio selection problem: A comparison of fuzzy goal programming and linear physical programming. Eur. J. Oper. Res. 6, 2, 121--128.Google Scholar
- Bin Li. 2015. Online Portfolio Selection: Principles and Algorithms. CRC Press, Boca Raton, FL.Google Scholar
- Bin Li and Steven C. H. Hoi. 2012. On-line portfolio selection with moving average reversion. In Proceedings of the International Conference on Machine Learning. 563--570. Google ScholarDigital Library
- Bin Li and Steven C. H. Hoi. 2012. Online portfolio selection: A survey. ACM Comput. Surveys 46, 3, 1--36. Google ScholarDigital Library
- Bin Li, Steven C. H. Hoi, and Vivekanand Gopalkrishnan. 2011. CORN: Correlation-driven nonparametric learning approach for portfolio selection. ACM Trans. Intell. Syst. Technol. 2, 3, 1--29. Google ScholarDigital Library
- Bin Li, Steven C. H. Hoi, Doyen Sahoo, and Zhi Yong Liu. 2015. Moving average reversion strategy for on-line portfolio selection. Artific. Intell. 222, 1, 104--123. Google ScholarDigital Library
- Bin Li, Steven C. H. Hoi, Peilin Zhao, and Vivekanand Gopalkrishnan. 2013. Confidence weighted mean reversion strategy for online portfolio selection. ACM Trans. Knowl. Discov. Data 7, 1, 1--38. Google ScholarDigital Library
- Bin Li, Doyen Sahoo, and Steven C. H. Hoi. 2016. OLPS: A toolbox for on-line portfolio selection. J. Mach. Learn. Res. 17, 35, 1--5. http://jmlr.org/papers/v17/15-317.html. Google ScholarDigital Library
- Bin Li, Jialei Wang, Dingjiang Huang, and Steven C. H. Hoi. 2017. Transaction cost optimization for online portfolio selection. Quant. Finance 2017, 1--14.Google Scholar
- Bin Li, Peilin Zhao, Steven C. H. Hoi, and Vivekanand Gopalkrishnan. 2012. PAMR: Passive aggressive mean reversion strategy for portfolio selection. Mach. Learn. 87, 2, 221--258. Google ScholarDigital Library
- Chenghao Liu, Steven C. H. Hoi, Peilin Zhao, and Jianling Sun. 2016. Online ARIMA algorithms for time series prediction. In Proceedings of the 30th AAAI Conference on Artificial Intelligence. 1867--1873. Google ScholarDigital Library
- Leandro L. Minku, Allan P. White, and Xin Yao. 2010. The impact of diversity on online ensemble learning in the presence of concept drift. IEEE Trans. Knowl. Data Eng. 22, 5, 730--742. Google ScholarDigital Library
- John Moody, Lizhong Wu, Yuansong Liao, and Matthew Saffell. 1998. Performance functions and reinforcement learning for trading systems and portfolios. J. Forecast. 17, 5--6, 441--470.Google ScholarCross Ref
- N. C. Oza. 2006. Online bagging and boosting. In Proceedings of the IEEE International Conference on Systems, Man, and Cybernetics, Vol. 3. 2340--2345.Google Scholar
- William F. Sharpe. 1963. A simplified model for portfolio analysis. Manage. Sci. 9, 2, 277--293. Google ScholarDigital Library
- William F. Sharpe. 1994. The sharpe ratio. J. Portfolio Manage. 21, 1, 49--58.Google ScholarCross Ref
- Weiwei Shen and Jun Wang. 2015. Transaction costs-aware portfolio optimization via fast Lowner-John ellipsoid approximation. In Proceedings of the 29th AAAI Conference on Artificial Intelligence. 1854--1860. Google ScholarDigital Library
- Weiwei Shen and Jun Wang. 2017. Portfolio selection via subset resampling. In Proceedings of the 31st AAAI Conference on Artificial Intelligence. 1517--1523.Google Scholar
- Christopher G. Small. 1990. A survey of multidimensional medians. Int. Stat. Rev. 58, 3, 263--277.Google ScholarCross Ref
- Symone Soares, Carlos Henggeler Antunes, and Arajo Rui. 2013. Comparison of a genetic algorithm and simulated annealing for automatic neural network ensemble development. Neurocomputing 121, 18, 498--511. Google ScholarDigital Library
- Edward O. Thorp. 1975. Portfolio choice and the Kelly criterion. In Stochastic Optimization Models in Finance. Elsevier, 599--619.Google Scholar
- Allan Timmermann. 2006. Forecast combinations. In Handbook of Economic Forecasting. Elsevier, 135--196.Google Scholar
- Theodoros Tsagaris, Ajay Jasra, and Niall M. Adams. 2012. Robust and adaptive algorithms for online portfolio. Quant. Finance 12, 11, 1651--1662.Google ScholarCross Ref
- William W. S. Wei and Christopher Chatfield. 1996. Some MINITAB and S-PLUS commands. In The Analysis of Time Series: An Introduction. CRC Texts in Statistical Science. Chapman 8 Hall/CRC Press, Boca Raton, FL, 303--304.Google Scholar
- Hongke Zhao, Qi Liu, Guifeng Wang, Yong Ge, and Enhong Chen. 2016. Portfolio selections in P2P lending: A multi-objective perspective. In Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2075--2084. Google ScholarDigital Library
- Hongke Zhao, Hefu Zhang, Yong Ge, Qi Liu, Enhong Chen, Huayu Li, and Le Wu. 2017. Tracking the dynamics in crowdfunding. In Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 625--634. Google ScholarDigital Library
- Zhi Hua Zhou. 2012. Ensemble Methods: Foundations and Algorithms. CRC Press, Boca Raton, FL. Google ScholarCross Ref
- Martin Zinkevich. 2003. Online convex programming and generalized infinitesimal gradient ascent. In Proceedings of the International Conference on Machine Learning. 928--936. Google ScholarDigital Library
- Hui Zou and Yuhong Yang. 2004. Combining time series models for forecasting. Int. J. Forecast. 20, 1, 69--84.Google ScholarCross Ref
Index Terms
- Combination Forecasting Reversion Strategy for Online Portfolio Selection
Recommendations
Confidence Weighted Mean Reversion Strategy for Online Portfolio Selection
Online portfolio selection has been attracting increasing attention from the data mining and machine learning communities. All existing online portfolio selection strategies focus on the first order information of a portfolio vector, though the second ...
Moving average reversion strategy for on-line portfolio selection
On-line portfolio selection, a fundamental problem in computational finance, has attracted increasing interest from artificial intelligence and machine learning communities in recent years. Empirical evidence shows that stock's high and low prices are ...
A Contrarian Trading Strategy: Mean vs. Median Reversion
ICEEG '23: Proceedings of the 2023 7th International Conference on E-Commerce, E-Business and E-GovernmentTo optimize the total cumulative wealth, it needs to rebalance the portfolio on a period-by-period basis, using previously published portfolio values. The median and mean reversion techniques are two contrarian trading strategies. Mean reversion is a ...
Comments