Improving Portfolio Performance Using a Novel Method for Predicting Financial Regimes (2310.04536v1)
Abstract: This work extends a previous work in regime detection, which allowed trading positions to be profitably adjusted when a new regime was detected, to ex ante prediction of regimes, leading to substantial performance improvements over the earlier model, over all three asset classes considered (equities, commodities, and foreign exchange), over a test period of four years. The proposed new model is also benchmarked over this same period against a hidden Markov model, the most popular current model for financial regime prediction, and against an appropriate index benchmark for each asset class, in the case of the commodities model having a test period cost-adjusted cumulative return over four times higher than that expected from the index. Notably, the proposed model makes use of a contrarian trading strategy, not uncommon in the financial industry but relatively unexplored in machine learning models. The model also makes use of frequent short positions, something not always desirable to investors due to issues of both financial risk and ethics; however, it is discussed how further work could remove this reliance on shorting and allow the construction of a long-only version of the model.
- A non-random walk down Wall Street. In A Non-Random Walk Down Wall Street. Princeton University Press, 2011.
- Testing the profitability of moving-average rules as a portfolio selection strategy. Pacific-Basin Finance Journal, 20(5):825–842, 2012.
- P.J. Kaufman. Smarter trading: Improving performance in changing markets. McGraw-Hill, New York, USA, 1995.
- Improving on the Markov-switching regression model by the use of an adaptive moving average. In New Perspectives and Paradigms in Applied Economics and Business: Select Proceedings of the 2022 6th International Conference on Applied Economics and Business, pages 17–30. Springer, 2023.
- H.M. Krolzig. Markov-switching vector autoregressions: Modelling, statistical inference, and application to business cycle analysis. Springer, New York, USA, 1997.
- Linear probability, logit, and probit models. Sage, 1984.
- Modeling and predicting US recessions using machine learning techniques. International Journal of Forecasting, 37(2):647–671, 2021.
- Statistical inference for probabilistic functions of finite state markov chains. The Annals of Mathematical Statistics, 37(6):1554–1563, 1966.
- Forecasting oil price trends using wavelets and hidden Markov models. Energy Economics, 32(6):1507–1519, 2010.
- Hidden Markov models for forex trends prediction. In 2014 International Conference on Information Science & Applications (ICISA), pages 1–4. IEEE, 2014.
- A hidden Markov model to detect regime changes in cryptoasset markets. Quality and Reliability Engineering International, 36(6):2057–2065, 2020.
- Leo Breiman. Random forests. Machine Learning, 45(1):5–32, 2001.
- Evaluating multiple classifiers for stock price direction prediction. Expert Systems with Applications, 42(20):7046–7056, 2015.
- Nikola Milosevic. Equity forecast: Predicting long term stock price movement using machine learning. arXiv preprint arXiv:1603.00751, 2016.
- Felix Ward. Spotting the danger zone: Forecasting financial crises with classification tree ensembles and many predictors. Journal of Applied Econometrics, 32(2):359–378, 2017.
- Jeremy Piger. Turning points and classification. Springer, 2020.
- Alireza Yazdani. Machine learning prediction of recessions: An imbalanced classification approach. The Journal of Financial Data Science, 2(4):21–32, 2020.
- A machine learning approach in regime-switching risk parity portfolios. The Journal of Financial Data Science, 3(2):87–108, 2021.
- Piotr Pomorski. Features and assets used in this work. https://figshare.com/articles/conference_contribution/LOD2023_appendix/23681205, 2023.
- JRM Hosking. Fractional differencing. Biometrika, 68:165–175, 1981.
- Distributed and parallel time series feature extraction for industrial big data applications. arXiv preprint arXiv:1610.07717, 2016.
- Optuna: A next-generation hyperparameter optimization framework. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pages 2623–2631, 2019.
- Marcos Lopez De Prado. Advances in Financial Machine Learning. John Wiley & Sons, 2018.
- Bias in random forest variable importance measures: Illustrations, sources and a solution. BMC Bioinformatics, 8(1):1–21, 2007.
- Feature selection with the Boruta package. Journal of Statistical Software, 36:1–13, 2010.
- C.L. Israelsen. A refinement to the Sharpe ratio and information ratio. Journal of Asset Management, 5(6):423–427, 2005.
- Brian W Matthews. Comparison of the predicted and observed secondary structure of T4 phage lysozyme. Biochimica et Biophysica Acta (BBA)-Protein Structure, 405(2):442–451, 1975.
- The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation. BMC Genomics, 21(1):1–13, 2020.
- Lloyd S Shapley et al. A value for n-person games, 1953.