Distributionally robust Kelly portfolio optimization based on MMD criterion
Subject Areas : Financial engineering
Asghar Zafari
1
,
Yaghoub Pourkarim
2
*
,
SayyedAli Paytakhti Oskooi
3
,
Mahdi Zeynali
4
,
Ahmad Mohammadi
5
1 - Department of Financial engineering, Tabriz Branch, Islamic Azad University, Tabriz, Iran.
2 - Department of Accounting, Tabriz Branch, Islamic Azad University, Tabriz, Iran
3 - Department of Economics, Tabriz Branch, Islamic Azad University, Tabriz, iran
4 - Department of Accounting, Tabriz Branch, Islamic Azad University, Tabriz, Iran
5 - Department of Accounting, Tabriz Branch, Islamic Azad University, Tabriz, Iran
Keywords: distributionally robust, Kelly portfolio, MMD.,
Abstract :
. be tested In order to solve this problem, in the present study, a general distribution stable stock portfolio with the criterion of the maximum difference of the mean of the worst-case Max-Min scenario is introduced. The scenarios include distributions in the neighborhood of the empirical distribution, where the radius of the neighborhood is controlled by the maximum mean difference criterion. Optimizing the distributed robust model of the overall stock portfolio based on the criterion of the maximum average difference on a statistical sample consisting of 252 5-member portfolios with a weekly time horizon of 10 assets and using the cumulative optimization algorithm of particles showed that the distributed robust portfolio in the Sharpe ratio criterion of Two equally weighted portfolios and the normal overall portfolio work better in such a way that the Sharpe ratio of the cumulative return of the proposed portfolio is more than 1.5 times the normal overall portfolio and 3 times the balanced portfolio. This article shows that distributional stabilization has a significant effect on improving risk-adjusted cumulative returns.
1) بیرانوند، منا؛ داودی، سید محمد رضا و شریفی قزوینی، محمدرضا. (1403). بهینه سازی سبد سهام استوار توزیعی براساس نسبت کالمار. نشریه مهندسی سیستم و بهره وری. 94-109.
2) Bermin, H. P., & Holm, M. (2022). Kelly trading and market equilibrium (No. 2019/2). Lund University, Knut Wicksell Centre for Financial Studies.
3) Carta, A., & Conversano, C. (2020). Practical Implementation of the Kelly Criterion: Optimal Growth Rate, Number of Trades, and Rebalancing Frequency for Equity Portfolios. Frontiers in Applied Mathematics and Statistics, 6, 577050.
4) Fan, W. L., & Anel, M. E. (2024). Robust Portfolio Choice under the Modified Constant Elasticity of Variance. Mathematics, 12(3), 440.
5) Gretton, A., Borgwardt, K. M., Rasch, M. J., Schölkopf, B., & Smola, A. (2012). A kernel two-sample test. The Journal of Machine Learning Research, 13(1), 723-773.
6) Hosseini-Nodeh, Z., Khanjani-Shiraz, R., & Pardalos, P. M. (2022). Distributionally Robust Portfolio Optimization with Second-Order Stochastic Dominance Based on Wasserstein Metric. Information Sciences.
7) Hsieh, C. H. (2020). Necessary and sufficient conditions for frequency-based Kelly optimal portfolio. IEEE Control Systems Letters, 5(1), 349-354.
8) Ji, R., Lejeune, M. A., & Fan, Z. (2022). Distributionally robust portfolio optimization with linearized STARR performance measure. Quantitative Finance, 1-15.
9) Li, J. Y. M. (2023). Wasserstein-Kelly Portfolios: A Robust Data-Driven Solution to Optimize Portfolio Growth. arXiv preprint arXiv:2302.13979.
10) Shihan Di, Dong Ma, Peibiao Zhao . (202. 3) 𝛼-robust portfolio optimization problem under the distribution uncertainty. Journal of Industrial and management Optimization, 19(4): 2528-2548.
11) Uehara, Y., Nishimura, N., Li, Y., Yang, J., Jobson, D., Ohashi, K., ... & Takano, Y. (2024). Robust portfolio optimization model for electronic coupon allocation. arXiv preprint arXiv:2405.12865.
12) Zhang, X. (2022). Distributional Robust Portfolio Construction based on Investor Aversion. arXiv preprint arXiv:2203.13999
13) Zhou, Y., & Xu, L. (2024). A new distributionally robust reward-risk model for portfolio optimization. Open Mathematics, 22(1), 20240010.