Optimizing the currency portfolio, a basis for designing an algorithmic trading system

Document Type : Original Article

Authors

1 Ph.D., Economics, University of Mazandaran, Babolsar, Iran.

2 Prof., Department of Economics, University of Tehran, Tehran, Iran.

Abstract

This article explores meta-heuristic methods for optimizing asset portfolios. It calculates the investment efficiency frontier, identifies the minimum risk portfolio, and computes the Sharpe ratio. Optimal currency baskets serve as signals for algorithmic trading, enhancing investment efficiency, particularly in volatile markets like currencies. The proposed algorithmic trading system is based on optimal currency basket selection.The method involves successive optimization of portfolios, using data mining concepts to determine the Value at Risk (VaR) for short-term portfolios. Key topics include non-linear exchange rate forecasting, VaR calculation via the EGARCH model, meta-heuristic optimization of portfolios, and algorithmic trading system design.
To address Markowitz model limitations, future exchange rate predictions using the RNN model are employed. Asset covariance considers exchange rate correlations, scaled by VaR. Random optimization calculates minimum values and asset weights for buying, holding, and selling signals. Selecting 9 out of 28 main currency rates minimizes systematic risk in day trading. Testing the system on 123 daily data points yielded a 27% total return (approximately 4.5% monthly), using only 10% of initial capital and considering transaction costs. The system’s maximum loss was 6%, and the maximum profit was 5.7%.

Keywords

Main Subjects

References

Abbasi, E., Samavi, M. E., & Koosha, E. (2020). Performance evaluation of the technical analysis indicators in comparison with the buy and hold strategy in tehran stock exchange indices. Advances in Mathematical Finance and Applications, 5(3), 285–301. [in Persian] Doi: 10.22034/amfa.2020.1893194.1376
Abdi, M., & Najafi, A. (2018). Online Portfolio Selection Using Spectral Pattern Matching. Financial Engineering and Portfolio Management, 9(34), 175-192. [in Persian]
Arad, H., Kaviani, M., & Kaviani, M. (2024). Portfolio formation strategy using modified SVAM, P/CF, and P/S ratios in Tehran Stock Exchange. Strategic Research on Budgeting and Finance. [in Persian]
Azizi Ganzagh, H., & Jafari Samimi, A. (2022). Forecasting inflation in Iran with two approaches of econometrics and artificial neural network; Comparison of NARDL, NARX nonlinear models. Journal of Econometric Modelling, 7(3), 39-68. [in Persian] Doi:  10.22075/jem.2022.26727.1716
Ganzagh, H. A., Samimi, A. J., Elmi, Z. M., & Tehranchian, A. M. (2023). Comparing Inflation Forecasting Models in Iran: New Evidences from ARDL-D-LSTM Model. Iranian Journal of Economic Research, 27(93), 149-176. [in Persian] Doi: 10.22054/ijer.2022.63376.1037
Borodin, A., El-Yaniv, R., & Gogan, V. (2003). Can we learn to beat the best stock. Advances in Neural Information Processing Systems, 16. Doi:10.1613/jair.1336
Chaboud, A. P., Chiquoine, B., Hjalmarsson, E., & Vega, C. (2014). Rise of the machines: Algorithmic trading in the foreign exchange market. The Journal of Finance, 69(5), 2045–2084. Doi: 10.1111/jofi.12186
Cohen, G. (2022). Algorithmic trading and financial forecasting using advanced artificial intelligence methodologies. Mathematics, 10(18), 3302. Doi: 10.3390/math10183302
Cover, T. M. (1991). Universal portfolios. Mathematical Finance, 1(1), 1–29. Doi: 10.1111/j.1467-9965.1991.tb00002.x
Cover, T. M., & Ordentlich, E. (1996). Universal portfolios with side information. IEEE Transactions on Information Theory, 42(2), 348–363. Doi: 10.1109/18.485708
Dempster, M. A. H., & Leemans, V. (2006). An automated FX trading system using adaptive reinforcement learning. Expert Systems with Applications, 30(3), 543–552. Doi: 10.1016/j.eswa.2005.10.012
Estrada, J. (2000). The cost of equity in emerging markets: a downside risk approach. Doi: 10.2139/ssrn.249579
Girardi, G., & Ergün, A. T. (2013). Systemic risk measurement: Multivariate GARCH estimation of CoVaR. Journal of Banking & Finance, 37(8), 3169–3180. Doi: 10.1016/j.jbankfin.2013.02.027
Ghasemiyeh, R., Sinaei, H., & Sahraei, S. (2023). Predicting liquidity in the Tehran Stock Exchange using learning models. Strategic Research on Budgeting and Finance, 4(3), 11-29. [in Persian] Dor: 20.1001.1.27171809.1402.4.3.1.5
Gordon, T. J. (1994). Cross-impact method (Vol. 4). American Council for the United Nations University.
Gouveia, A. N. C. (2020). Machine Learning Applications on Algorithmic Trading in the Foreign Exchange Market. Universidade NOVA de Lisboa (Portugal).
Györfi, L., Udina, F., & Walk, H. (2008). Nonparametric nearest neighbor based empirical portfolio selection strategies. Doi: 10.1524/stnd.2008.0917
Hendershott, T., Jones, C. M., & Menkveld, A. J. (2011). Does algorithmic trading improve liquidity? The Journal of Finance, 66(1), 1–33. Doi: 10.1111/j.1540-6261.2010.01624.x
Hornik, K. (1993). Some new results on neural network approximation. Neural Networks, 6(8), 1069–1072. Doi: 10.1016/S0893-6080(09)80018-X
Jin, B. (2023). A Mean-VaR Based Deep Reinforcement Learning Framework for Practical Algorithmic Trading. IEEE Access, 11, 28920–28933. Doi: 10.1109/ACCESS.2023.3259108
Kim, S. E., & Seo, I. W. (2015). Artificial Neural Network ensemble modeling with conjunctive data clustering for water quality prediction in rivers. Journal of Hydro-Environment Research, 9(3), 325–339. Doi: 10.1016/j.jher.2014.09.006
Lin, T., Horne, B. G., & Giles, C. L. (1998). How embedded memory in recurrent neural network architectures helps learning long-term temporal dependencies. Neural Networks, 11(5), 861–868. Doi: 10.1016/s0893-6080(98)00018-5
Mihatsch, O., & Neuneier, R. (2002). Risk-sensitive reinforcement learning. Machine Learning, 49, 267–290. Doi: 10.48550/arXiv.1311.2097
Adabi firouzjaee B, Mehrara, M., & Mohammadi, S. (2016). Estimation and Evaluation of Tehran Stock Exchange Value at Risk Based on Window Simulation Method. Journal of Economic Modeling Research, 7(23), 35-73. [in Persian] Doi: 10.18869/acadpub.jemr.6.23.35
Mousavi Loletti, S. A., Ghanbari, H., & Mohammadi, O. (2024). Portfolio optimization using the semi-variance model with an emphasis on positive potential (Case study: Tehran Stock Exchange). Strategic Research on Budgeting and Finance, 5(1), 57-78. [in Persian] Doi: 20.1001.1.27171809.1403.5.1.3.0
Nelson, D. B. (1991). Conditional heteroskedasticity in asset returns: A new approach. Econometrica: Journal of the Econometric Society, 347–370. Doi: 10.2307/2938260
Neuneier, R. (1997). Enhancing Q-learning for optimal asset allocation. Advances in Neural Information Processing Systems, 10.
Rastegar, M. A., & Dastpak, M. (2018). Developing a High-Frequency Trading system with Dynamic Portfolio Management using Reinforcement Learning in Iran Stock Market. Financial Research Journal, 20(1), 1-16. [in Persian] Doi: 10.22059/jfr.2017.230613.1006415
Tang, S. (2022). Measurement and Management of Interest Rate Risk of Commercial Banks: Based on VaR-GARCH Model of a Case Study of SHIBOR. Scientific and Social Research, 4(1), 89–100.
Budget and Finance Strategic Research
Volume 5, Issue 4 - Serial Number 20
Winter Quarterly
December 2024
Pages 11-70

Files

History

  • Receive Date: 29 July 2024
  • Revise Date: 12 September 2024
  • Accept Date: 08 December 2024

Share

How to cite

Statistics